id
stringlengths 12
15
| title
stringlengths 8
162
| content
stringlengths 1
17.6k
| prechunk_id
stringlengths 0
15
| postchunk_id
stringlengths 0
15
| arxiv_id
stringlengths 10
10
| references
listlengths 1
1
|
|---|---|---|---|---|---|---|
2308.03210#0 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 3 2 0 2 g u A 9 ] G L . s c [ 2 v 0 1 2 3 0 . 8 0 3 2 : v i X r a # Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series # Chrysoula Kosma ´Ecole Polytechnique, IP Paris France [email protected] # Giannis Nikolentzos ´Ecole Polytechnique, IP Paris France [email protected] Michalis Vazirgiannis ´Ecole Polytechnique, IP Paris France [email protected] # Abstract | 2308.03210#1 | 2308.03210 | [
"1710.04110"
]
|
|
2308.03210#1 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Irregularly sampled multivariate time series are ubiquitous in several application domains, leading to sparse, not fully-observed and non-aligned observations across different variables. Standard sequential neural network architectures, such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), consider regular spacing between observation times, posing significant challenges to irregular time series modeling. While most of the proposed architectures incorporate RNN variants to handle irregular time intervals, convolutional neural networks have not been adequately studied in the irregular sampling setting. In this paper, we parameterize convolutional layers by employing time-explicitly initialized kernels. Such general functions of time enhance the learning process of continuous-time hidden dynamics and can be efficiently incorporated into convolutional kernel weights. We, thus, propose the time-parameterized convolutional neural network (TPCNN), which shares similar properties with vanilla convolutions but is carefully designed for irregularly sampled time series. We evaluate TPCNN on both interpolation and classification tasks involving real-world irregularly sampled multivariate time series datasets. Our experimental results indicate the competitive performance of the proposed TPCNN model which is also significantly more efficient than other state-of-the-art methods. At the same time, the proposed architecture allows the interpretability of the input series by leveraging the combination of learnable time functions that improve the network performance in subsequent tasks and expedite the inaugural application of convolutions in this field. | 2308.03210#0 | 2308.03210#2 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#2 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 1 # Introduction Time series arise naturally in many contexts including quantitative finance, astrophysics and medicine, just to name a few. Recently, there is a growing interest in applying machine learning techniques to time series data. Besides time series forecasting, which has been extensively studied for decades [7], other tasks have also emerged recently such as time series classification [12] and generation [8]. Time series are constructed from real-world data and usually several of their observations are missing or are subject to noise. This is mainly due to irregular sampling and is common in different types of data including medical records, network traffic, and astronomical data. Unfortunately, the most successful machine learning models in sequential modeling, namely recurrent neural networks (RNNs) and convolutional neural networks (CNNs) cannot properly handle such irregularly sampled time series data. Indeed, those models treat observations successively and assume an equidistant sampling scheme. Thus, time series data that | 2308.03210#1 | 2308.03210#3 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#3 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 1 exhibits variable gaps between consecutive time points pose a significant challenge to such conventional deep learning architectures. A naive approach to deal with the above problem would be to drop some observations such that the distance between consecutive (remaining) observations is fixed. However, this would increase data sparsity, thus leading to poorly defined latent variables. A more prominent approach would be to first apply some imputation method to replace missing values with estimated values, and then to use the standard models which assume an equidistant sampling scheme. In fact, several recent approaches build on the above idea [3, 9]. However, this could potentially result in a loss of information and a violation of the underlying dynamics. Recently, there has been an increasing interest in effectively capturing the continuous dynamics of real- world sparse and irregular multivariate time series. Most studies have extended RNNs to continuous-time hidden dynamics defined by ordinary differential equations (ODEs) [4, 24]. The effectiveness of Convolutional Neural Networks (CNNs) [15] as an alternative to recurrent architectures has been established, as long as the input dependencies that are essential fall within the memory horizon of the network. CNNs are based on parallel computations and thus are more efficient, contrary to the training instability and gradient problems of RNNs that employ back-propagation through time [34]. However, since discrete convolutions learn independent weights for each time step in the kernel range, they do not directly capture the time irregularities. Efforts for the continuous implementation of convolutional kernels have targeted 3D data [25, 33] and recently, sequences [23]. The proposed continuous convolution for sequential data [23], CKConv, parameterizes the kernel values using a multi-layer perception (MLP) on the relative positions of the observations, followed by a periodic activation function [29]. In contrast to [23] that take advantage of periodic activations, our layer can be constructed employing any predefined set of continuous functions and be followed by any activation, while using significantly fewer learnable parameters, since a single feed-forward layer is used for the parameterization of the convolutional kernel. Following the above line of research, in this paper, we develop a new model, so-called Time-Parameterized Convolutional Neural Network (TPCNN), which generalizes the standard CNN model to irregularly sampled time series. | 2308.03210#2 | 2308.03210#4 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#4 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | To achieve that, we replace the fixed kernels of CNNs with kernels whose values are parameterized both by time and by trainable variables. Thus, instead of keeping the kernel weights fixed over the whole time series length, we use different functions (e.g., linear, sinusoidal) to produce the kernels that will be convolved with each patch of the time series. Therefore, kernels can be seen as continuous functions of time, and the proposed TPCNN model can naturally learn continuous latent representations of irregular time series. Furthermore, the use of the aforementioned functions improves the explainability of the proposed model. We combine our time-parameterized convolutions with vanilla convolutions by stacking them in a deep encoder module. The proposed TPCNN model is evaluated in the tasks of time series classification and time series interpolation. Our experiments demonstrate that the proposed model performs comparably to state-of-the-art methods. The main contributions of the paper are summarized as follows: (i) Generalizing conventional, fixed convolutional kernels to time functions, that increase their represen- tational power and still leverage properties of convolutions (e.g., locally aggregated information, fast training). (ii) Enabling the application and proving the efficiency of deep stacked convolutions in the irregular sampling setting. (iii) Achieving high-performance results in interpolation and classification of irregularly sampled benchmark datasets, which are comparable to other state-of-the-art methods. # 2 Related Work The long-standing challenge in multivariate irregular time series modeling has led to the development of various neural network architectures that explicitly handle such time-dependent peculiarity. One strategy suggests dividing the timeline into equal intervals, filling in missing data, and then using a Recurrent Neural Network (RNN) on the imputed inputs. Using a weighted average between the empirical | 2308.03210#3 | 2308.03210#5 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#5 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 2 mean and the previous observation to perform imputation has also been proposed [3]. Alternative methods for imputation include the use of Gaussian processes [9], or generative adversarial networks [16] prior to running the RNN on time-discretized inputs. The interpolation-prediction network [26] employs several semi-parametric interpolation layers for multivariate time series input with missing values, followed by a prediction network which is applied on the produced regularly spaced and fully observed representations. Multi- directional RNNs (M-RNN) combine past and future observations for each timestamp [36]. A differentiable set function method for classifying irregularly sampled is another line of work presented in [11]. An alternative strategy for handling irregularly sampled data involves architectures that directly model such temporal sequences. Various techniques, including adaptations of gated recurrent unit networks (GRUs) [5] and Long Short-term Memory networks (LSTMs) [10], have been introduced for this purpose. Among the several proposed modified GRU architectures [3], a prominent example takes as input observed values, indicators denoting missing data points, and the differences in time between observations. The LSTM architecture has been extended for handling the time irregularity of the data, by introducing a novel time gate in [19] that updates the memory state. The activation and deactivation of this gate are governed by distinct rhythmic oscillations, controlled by some learnable parameters. Another LSTM modification is presented in [21], where the proposed forget gate moderates the passing of memory from one time step to another. Another solution for handling irregularly sampled data is to incorporate the time gaps between observations directly into Recurrent Neural Networks (RNNs). One approach is to add the time gap â t to the RNN input, which has been found to be susceptible to overfitting [18]. An alternative method is to introduce hidden states that decay over time, which has been proposed in several works as a viable solution [3, 2, 22]. Hidden states with an exponential decay can be employed to parameterize neural Hawkes processes and explicitly model observations via latent state changes at each observation event [17]. Many works focus on the continuous modeling of time series by learning a continuous-time neural representation with a latent state defined at all times. More specifically, a variational auto-encoder model, which utilizes a neural network decoder in combination with a latent ordinary differential equation (ODE) model, has been presented in [4]. | 2308.03210#4 | 2308.03210#6 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#6 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Based on this approach, an ODE-RNN encoder that consists of a neural ODE part that models the hidden state dynamics and an RNN part that updates the hidden state has been proposed [24]. A continuous version of the GRU architecture models the input series via continuous ODE dynamics describing the evolution of the probability distribution of the data [6]. Finally, an alternative to Neural ODEs, Neural Controlled Differential Equations represent the continuous-time analogue of an RNN, which benefits from memory-efficient adjoint-based backpropagation across observations [14]. Attention mechanisms combined with time encodings, as an alternative to positional ones [32], have been proposed [30, 37, 31]. By extending attention with learnable time embeddings [35], the recently proposed Multi-Time Attention Network [27] computes the similarity between observations at different time points using a learnable time embedding. This approach works similarly to kernel-based interpolation, but by leveraging a learnable time attention-based similarity kernel. Except for the optimization issues of RNNs, the conventional dot-product self-attention mechanism matches queries with keys without considering the surrounding context. At the same time, space complexity grows quadratically with the input length, leading to memory constraints and potential performance limitations. The use of implicit neural representations for creating continuous data representations by encoding the input in the weights of a neural network has recently gathered interest [20, 29]. Our approach can be conceptualized as an implicit representation of the convolutional kernels since they are parameterized as learnable and continuous functions of time. In this study, the proposed time-parameterized convolutional layer (TPC) introduces time-varying convolutional kernels, allowing for more efficient representational learning of the time dependencies among partially-observed variables. We leverage several continuous time functions for extracting learnable time embeddings of the time intervals across different variables. The proposed architecture is carefully designed for interpolation and classification tasks on irregularly sampled time series. | 2308.03210#5 | 2308.03210#7 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#7 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 3 # 3 The TPC Layer In this section, we define the mathematical properties of the employed Time-Parameterized layer (TPC) and analytically explain a proposed framework for tasks involving irregularly sampled, partially observed and multivariate time series. # 3.1 Preliminaries Convolution is a well-studied mathematical operation which has applications in many diverse scientific g, expresses how the shape of one is fields [1]. The convolution of two functions f and g, denoted by f modified by the other. Continuous convolution. the integral of the product of the two functions after one is reflected and shifted. Formally, given f : RD and g : RD â | 2308.03210#6 | 2308.03210#8 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#8 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | (f * 9)(x) = [. F(y)g(x â y)dy # (f Discrete convolution. the support domain of finite integer set ZD and equivalent of convolution is defined as: In the real world, signals are discrete and finite. For functions f , g, defined over D, respectively, the discrete } K, K + 1, ..., K 1, K {â â â (fe gin]= So flr â kolk) (1) k=â -K | 2308.03210#7 | 2308.03210#9 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#9 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Thus, the integral is replaced by a finite summation. Standard CNN models consist of layers that perform discrete convolutions that are defined over the discrete domain. # 3.2 Time-Parameterized 1D Convolutions We first introduce the key notations behind the employed time-parameterized convolutions for irregular and multivariate time series and analyze their fundamental properties. Irregular time series and standard CNNs. Let {Kâ ,...,X)} be a collection of multivariate time series where X â ¬ Râ ¢*Â¥ for all i â ¬ {1,...,N}. Thus, each time series consists of m channels and has a length (i.e., number of observations) equal to L which corresponds to the observation times {t1,t2,...,tz}. Let also d(-,-) denote a function that measures the distance (in time) between observations of a single channel of the collection of time series. The convolution operation of standard CNNs assumes that consecutive observations are equally spaced across all samples, and thus, the weights of the different kernels of standard CNNs are fixed across all chunks of the time series. In other words, the summation in the right part of Equation (i) is performed over the elements of the same set for all n. Formally, we have that d(X{),XÂ¥} 41) = T holds for alli â ¬ {1,...,m},j â ¬ {],..., Lâ 1} and i,j â ¬ {1,...,.N} where N is the number of samples. However, the above does not necessarily hold in the case of irregularly sampled time series data. Indeed, irregular sampling for multivariate series leads to variations in the number of observations across channels. Thus, due to the assumptions it makes, the standard convolution operation of CNNs is not suitable for irregular time series data. | 2308.03210#8 | 2308.03210#10 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#10 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 4 Time-parameterized convolutional kernels. To deal with the irregularity of time series, we propose to use time-parameterized kernels. Thus, instead of a fixed kernel that slides over the patches of the time series, we use a parameterized kernel whose components are functions of time. The kernel is also parameterized by N0 where the weights of a neural network. We constraint the size of the kernel to be equal to 2z + 1 where z N0 denotes the set of natural numbers together with zero. Then, the elements of the kernel are constructed by some function g(θ, â t) where θ denotes some trainable parameters and â t denotes the distance (in time) of the observation associated with some element of the kernel and the z + 1-th observation. Formally, the convolution is defined as follows: 2241 2241 (f*9)(t) = D> fltig(,t - ti) = SO f(ti)g(0, At) (2) i=1 i=1 where t1, . . . , t2z+1 are the timestamps associated with the observations of the patch the kernel is applied to. The function g(θ, â t) is quite general and can have different forms. In this paper, we focus on inter- R is defined as follows: 4 Ad") a( [a % Os 4 Ad") =61((n(os ar) +6) # g where h : R R denotes some activation function (i.e., sigmoid, ReLU, etc.). Thus, to construct each element of the kernel, function g takes as input four trainable parameters (i.e., θ1, θ2, θ3 and θ4) and the time difference between the current observation and the center observation of the patch. Function h is chosen such that inductive bias is injected into the model. This can allow the model to capture patterns that commonly occur in time series data and also make its internal operations more interpretable. For example, a function h(x) = c where c is some constant would not be a good candidate for extracting useful features from the time series. On the other hand, we employ more informative functions which can capture useful properties of time series such as trend and seasonality. In particular, we employ the following ten functions: | 2308.03210#9 | 2308.03210#11 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#11 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 1. h1(x) = x 6. h6(x) = x2 2. h2(x) = sin(x) 7. h7(x) = x3 3. h3(x) = cos(x) 8. h8(x) = sinh(x) 4. h4(x) = tan(x) 9. h9(x) = cosh(x) 5. h5(x) = exp(x) 10. h10(x) = tanh(x) Most of the time, trend is a monotonic function, and therefore, functions h1, h6 and h7 are chosen to detect trend in time series. Seasonality is a typical characteristic of time series in which the data experiences regular and predictable changes that recur over a defined cycle. Functions h2, h3, h9 and h10 are responsible for extracting features that take seasonality into account. The approach presented above generates kernels for univariate time series. In the case of multivariate time series, different parameters are learned for the different components of the time series. | 2308.03210#10 | 2308.03210#12 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#12 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Therefore, the Rm. Thus, four parameters (θ1, θ2, θ3 and θ4) are replaced by vectors of dimension m, i. e., θ1, θ2, θ3, θ4 function g(θ, â t) : R4m+1 Rm is computed by applying function h( ) pointwise to m different elements. · Note that â t is still a scalar since observation times are identical across all components of the series. # 3.3 The Time-Parameterized Convolutional (TPC) Layer Given a sample X(i), its corresponding observation times g, the kernel centered at the j-th observation (i. e., X(i) t1, t2, . . . , tL { , and a time-parameterized function } :,j ) is constructed as follows: | 2308.03210#11 | 2308.03210#13 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#13 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 5 Patch Observation time Difference in time Kernel X(i) :,jâ K tjâ K â tjâ K g(θ, â tjâ K ) . . . . . . . . . . . . X(i) :,j tj 0 g(θ, 0) . . . . . . . . . . . . X(i) :,j+K tj+K â tj+K g(θ, â tj+K ) Note that X(i) convolution is computed as follows: :,j denotes the j-th column of matrix X(i). Once we construct the kernel, the output of the m c=) 2G, Ati) Xf) pe +--+ D> G(9,0). Kf) +... l=1 l M: Il a + > 9, Ath XO Lj+kK M: l Il a # l,j+K R. | 2308.03210#12 | 2308.03210#14 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#14 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | In some cases, features of the multivariate time series might be missing. In such cases, the where c above operation would compute the sum of a smaller number of terms (since missing features are ignored). Thus, we also experimented with the mean function: fe m ; c= £(So0.as-1)1%)5 + + 9(0,0). Xf? +... 1=1 l=1 (3) m t Ss 99, Atj+K)i X.1) l=1 where ν denotes the actual number of features (out of the (2K + 1)m features, those that are not missing). Thus, the convolution between a sequence of observations and the kernel outputs a real number. | 2308.03210#13 | 2308.03210#15 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#15 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | We use RL. Furthermore, zero padding and apply the kernel to all observations and, therefore we obtain a vector c similar to standard CNNs, not a single kernel, but instead a collection of kernels is generated and applied to the input. These kernels might correspond to different functions of the ones defined above (i. e., h1, . . . , h10). Suppose that we use p different kernels in total (potentially of different functions). Then, the output of the TPC layer of the multivariate and irregularly sampled time series X(i) is computed as: TPO(X,t) = ||P co, E RU*P | 2308.03210#14 | 2308.03210#16 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#16 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | â is the concatenation operator between vectors and t(i) is a vector that stores the observation times where of the time series. â ¥ # 3.4 Properties of TPC Layer Constant number of parameters An interesting property of the TPC layer is that the number of parameters of each kernel is constant and equal to 4m regardless of the size of the kernel. This is because the kernel is dynamically generated based on the observation times and only 4m trainable parameters are involved. This is in contrast to standard convolutional layers where the number of parameters is equal to the size of the kernel plus the bias. Thus, the number of parameters of the TPC layer will be less than the number of parameters of a standard convolutional layer when the size of the kernels is greater than 4. This is likely to lead to less complex models and might significantly reduce overfitting. | 2308.03210#15 | 2308.03210#17 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#17 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | (Lâ mp) for kernel Time Complexity. The time complexity of the proposed TPC layer is approximately size â , similar to the vanilla 1D convolution. Since TPC relies on convolutions, that take advantage of parallel computations, it can be trained faster than recurrent neural network architectures. The complexity comparison becomes even more advantageous when compared with continuous-time models, such as neural ODEs that are significantly slower than RNNs [14]. 6 , \ 4 ' 1 1 1 2 1 1 â ' an(t) Ae \ 1 / i : Doak = 1 1 ' â ' ran A 1 a(t) |v ' a(t) | Tinear ' â 1 1 1 ' {tists ...stu} ' {tista,...5tz} i al TPc | : am(t) ' 1 ' ' f Mask â ' 1 1 Â¥ 1 a(t) |/ 1 ' ' t TPC } 1 1 ' 1 1 1 \ ' Figure 1: (Left) An encoder that consists of the proposed TPC layer, convolutions and pooling layer and produces a fixed-size latent representation z. (Right) An encoder-decoder framework that reconstructs the series from the input using TPC and linear layers. Learning Properties. The proposed TCP layer introduces time-varying convolutional kernels as opposed to fixed kernels that are commonly employed in traditional convolutional neural networks (CNNs). In other words, the employed kernels do not remain fixed throughout the whole length of the input series. This particular trait of TPC does not explicitly force weight sharing between different subsequences of the time series during convolution. Weight sharing is, however, implicitly modeled via the learnable representations of time, that are used to initialize the kernel weights. This is based on the assumption that observations that are mapped to similar time embeddings will probably share similar values of weights in the convolutional operation. The proposed approach still maintains the ability to locally aggregate information by retaining the notion of fixed kernel size in the convolution operation. This allows for the output of the convolution to be locally aggregated, while still incorporating the benefits of time-varying convolutional kernels. Invariance Properties. | 2308.03210#16 | 2308.03210#18 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#18 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | If some patterns in the time series are identical, both in terms of the ob- servations and also in terms of the difference in time between the observations, then the TPC layer will produce the same output for those two patterns. For example, let xi = (xiâ K, . . . , xi, . . . , xi+K) and xj = (xjâ K, . . . , xj, . . . , xj+K) denote two sequences of values and ti = (tiâ K, . . . , ti, . . . , ti+K) and tj = (tjâ K, . . . , tj, . . . , tj+K) denote their respective observation times. If xi = xj holds and â ti = â tj also holds, where â ti = (tiâ K tj), then the kernels produced for these two sequences of values are identical and therefore, the layer produces the same output. Furthermore, the different functions defined in the previous subsection make the kernels invariant to different transformations. For instance, in the above example, suppose that â ti = â tj, and that the k-th element of the second sequence is equal to (k + 1)2Ï times the corresponding element of the first sequence for ) function) and with . Then, the TPC layer equipped with the h2 function (i. e., sin( 0, 1, . . . , 2K + 1 k · } θ3 = 1 and θ4 = 0 would produce the same output for both patterns. Such a function can capture periodic temporal correlations. | 2308.03210#17 | 2308.03210#19 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#19 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 7 # 3.5 TPCNN Framework for Irregularly Sampled Time Series We will next discuss how the TPC layer can be integrated into neural network architectures for dealing with various tasks that involve irregular time series, such as interpolation and classification. Following previous work, we propose an encoder-decoder framework, so-called Time-Parameterized Convolutional Neural Network (TPCNN) framework. In what follows, we give more details about the two main components of the proposed framework, namely its encoder and its decoder. TPCNN Encoder. This module is responsible for mapping the input time series into a latent vector which captures their overall shape and their specificities. The first layer of the encoder is an instance of the TPC Rmà L layer introduced above. The TPC layer receives as input the irregular and multivariate series X(i) and the corresponding vector of observation times t(i) = . The output of TPC layer is then } successively fed to vanilla convolution layers which can capture longer-time dependencies of the continuous latent representation of the time series. A pooling layer follows each convolution layer, including TPC. By down-sampling the output, such layers are expected to extract features that are good indicators of class membership or of the shape of the time series. Finally, a fully-connected layer is applied to the output of the last convolution layer to extract a low-dimensional representation z(i) | 2308.03210#18 | 2308.03210#20 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#20 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | â TPCNN Decoder. This part of the architecture is responsible for reconstructing the multivariate input series from the latent vector that is produced by the encoder. The latent vector z that was produced by the encoder is first given as input to a fully-connected layer whose objective is to perform rescaling. The emerging vector is then passed onto another fully-connected layer which produces a matrix Ë X(i) that matches the dimension of the input time series. These reconstructed time series are then compared against the input series to evaluate the autoencoderâ | 2308.03210#19 | 2308.03210#21 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#21 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | s performance. Interpolation and Classification Setting. Note that some components of the TPCNN framework depend on the considered task, i. e., interpolation or classification. For instance, in the interpolation setting, each time a kernel of the TPC layer is applied to some subset of the input series, the observation that lies at the center of that subset is masked such that the model does not have direct access to it. On the other hand, such a masking is not performed in the case of the classification setting. The reconstruction loss of a standard autoencoder is typically measured using the mean squared error (MSE) between the original input and the reconstructed output. For an input time series X(i), the MSE loss is computed as: 1 ; ~ 2 Linterpolation = iol y x? - xO N, | jeO is a set that contains the indices of the observed values and Ë X(i) denotes the reconstructed series where produced by the decoder as a function of the latent vector z. | 2308.03210#20 | 2308.03210#22 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#22 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | O The encoder-decoder framework of Figure 1 (Right) is combined with the MSE loss for the interpolation task. Additionally, as already discussed, masking is performed on the center element of each slice of the input series, and the rest of the observed values of the slice are used for interpolation. In the case of classification, the latent representation z that is generated by the encoder and which preserves the information about the multivariate time seriesâ dependencies, can be directly fed to a classifier module to make predictions. In the experiments that follow, we employ a 2-layer multi-layer perceptron (MLP) with ReLU activation function. Thus, in the case of a classification problem with classes, the output is computed as follows: p = sof tmax(M LP (z)) Then, given a training set consisting of time series X(1), . . . , X(N ), we use the negative log-likelihood of the correct labels as training loss: N Ie Lelassi fication = â Ss Ss y$â log p\? i=1 j=1 # L 8 # where y(i) j is equal to 1 if X(i) belongs to the j-th class, and 0 otherwise. The application of the TPCNN model to the above two scenarios is illustrated in Figure 1 (classification on the left and interpolation on the right). | 2308.03210#21 | 2308.03210#23 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#23 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | # 4 Experiments In this section, we describe the experimental setup and methodology used to evaluate the performance of our proposed time-parameterized convolutional layer on various tasks involving irregular time series, including interpolation and classification. # 4.1 Datasets We evaluate the performance of the proposed architecture and the baselines on the following real-world datasets: PhysioNet: The PhysioNet Challenge 2012 dataset [28] comprises 8000 multivariate time series that correspond to records from the first 48 hours of a patientâ s admission to the intensive care unit (ICU). Measurements include 37 variables which can be missing at different steps and occur in irregular intervals. Half of the instances are labeled with 13.8% of instances being in the positive class (in-hospital mortality). For the interpolation experiments, we used all 8000 instances and for the classification experiments, we used the 4000 labeled instances. We use the same experimental protocols and preprocessing steps as in [24]. MIMIC-III: The MIMIC-III dataset [13] consists of multivariate health records, that can have missing values, collected at Beth Israel Deaconess Medical Center between 2001 and 2012. Based again on the preprocessing strategy of [24], we extract 53211 samples including 12 features. Given the first 48 hours of data, the task is to predict in-hospital mortality, with 8.1% of the data samples in the positive class. | 2308.03210#22 | 2308.03210#24 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#24 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Human Activity: The human activity dataset contains time series data from five individuals performing various activities (such as walking, sitting, lying, standing, etc.), based on the 3D positions of tags attached to their belts, chest and ankles (12 features in total). Following the preprocessing procedures outlined by [24], a dataset of 6554 sequences and 50 time steps is extracted. The task for this dataset is to classify each time step in the series into one of the eleven activities. # 4.2 Experimental Setting We next explain the experimental setting we follow for interpolation and classification, similar to the work of [27]. In the case of interpolation, we study all instances (labeled and unlabeled) from the PhysioNet dataset. The dataset is partitioned into an 80% training set and a 20% test set, with a fraction (20%) of the training data serving as the validation set. The interpolation task is to predict based on a subset of available data points values for the unobserved points. This is executed using different percentages of observed steps, which vary between 50% and 90% of the total available steps. For this experiment, we perform five different runs and report performance on the unobserved data using the mean squared error (MSE) metric. We also use the labeled data from the PhysioNet, MIMIC-III and Human Activity datasets to conduct classification experiments. For the physiological data of PhysioNet and MIMIC-III, the classification task considers the entire time series, whereas, in the context of the human activity dataset, classification is performed for each time step in the series. We follow the same train, validation and test splitting procedure as described in the interpolation setting. For this experiment, we perform five different runs to provide the classification performance on the different datasets. For PhysioNet and MIMIC-III datasets, we report performance using the area under the ROC curve (AUC) score, due to class imbalance. For the Human Activity dataset, we asses the model performance using the accuracy metric. The validation set is used to select the best set of hyperparameters for our models via grid search. | 2308.03210#23 | 2308.03210#25 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#25 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 9 Table 1: Performance for interpolation with different percentages of observed time points on PhysioNet. We mention in bold the best-performing method(s) and underline the second best-performing method(s) based on statistical significance tests. Model RNN-VAE L-ODE-RNN L-ODE-ODE mTAND-Full TPCNN (ours) Observed(%) 13.418 ± 0.008 8.132 ± 0.020 6.721 ± 0.109 4.139 ± 0.029 5.993 ± 0.058 50% Mean Squared Error (à | 2308.03210#24 | 2308.03210#26 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#26 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 10â 3) 11.887 ± 0.007 8.171 ± 0.030 6.798 ± 0.143 4.157 ± 0.053 5.654 ± 0.108 70% 12.594 ± 0.004 8.140 ± 0.018 6.816 ± 0.045 4.018 ± 0.048 5.797 ± 0.063 60% 11.133 ± 0.007 8.143 ± 0.025 6.850 ± 0.066 4.410 ± 0.149 5.624 ± 0.084 80% 11.470 ± 0.006 8.402 ± 0.022 7.142 ± 0.066 4.798 ± 0.036 5.532 ± 0.140 90% # 4.3 Baseline Models In this study, we conduct a thorough evaluation of several deep learning architectures as baseline models for performance comparison. These models are specifically designed to handle irregular time series and include variations of the Recurrent Neural Network (RNN), Attention modules and encoder-decoder architectures. The specific models evaluated in this study include: (i) Basic RNN variants including: RNN-Impute, RNN-â t, RNN-decay, GRU-D. The RNN-Impute model employs a method to impute missing data points based on the weighted average between the last observation of the time series and the total mean of the variable in the training set [3]. In RNN-â t the input to RNN is extended with a missing indicator for the variable and the time interval â t since the last observed point. The RNN-decay is an RNN with hidden states that decay exponentially over time [18, 3], whereas GRU-D employs exponential decay on both hidden states and input [3]. (ii) Other RNN variants, such as Phased-LSTM, IP-Nets, SeFT, RNN-VAE. The Phased-LSTM model incorporates time irregularity through the use of a time gate that controls access to the hidden and cell states of the LSTM [19]. | 2308.03210#25 | 2308.03210#27 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#27 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | IP-Nets are Interpolation-Prediction Networks (IPN), which perform interpolation prior to prediction with an RNN on the transformed equally-spaced intervals, using semi-parametric interpolation layers [26]. The SeFT model employs learnable set functions for time series and combines the representations with an attention-based mechanism [11]. RNN-VAE is a standard variational RNN encoder-decoder. (iii) ODE variants, such as ODE-RNN, L-ODE-RNN, L-ODE-ODE. In ODE-RNN neural ODEs model the dynamics of the hidden state, and an RNN updates the hidden state in the presence of new observations [24]. Similarly, L-ODE-RNN and L-ODE-ODE are latent ODEs with the former combining an RNN encoder and a neural ODE decoder [4], and the latter an ODE-RNN encoder and a neural ODE decoder [24]. (iv) Attention-based frameworks, including mTAND. The multi-time attention network, mTAND, interpo- lates missing data using a learnable attention similarity kernel between observations, which are accessed based on trainable temporal embeddings [27]. | 2308.03210#26 | 2308.03210#28 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#28 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | # 4.4 Results Interpolation of missing data. In Table 1 we present the results of the experimental setting designed for interpolation, as described in Section 4.2. For different percentages of observed values (i. e., ranging from 50% to 90%), we record the interpolation performance on the reconstructed irregularly sampled multivariate time series of the PhysioNet dataset using the MSE metric. We compare the proposed TPCNN model to different 10 Table 2: Performance for per-sequence classification on PhysioNet and MIMIC-III and per-time-point classification on Human Activity datasets. We mention in bold the best-performing method(s) and underline the second best-performing method(s) based on statistical significance tests. Model PhysioNet 0.764 ± 0.016 RNN-Impute 0.787 ± 0.014 RNN-â | 2308.03210#27 | 2308.03210#29 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#29 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | t 0.807 ± 0.003 RNN-Decay RNN GRU-D 0.818 ± 0.008 Phased-LSTM 0.836 ± 0.003 0.819 ± 0.006 IP-Nets 0.795 ± 0.015 SeFT 0.515 ± 0.040 RNN-VAE 0.833 ± 0.009 ODE-RNN 0.781 ± 0.018 L-ODE-RNN 0.829 ± 0.004 L-ODE-ODE mTAND-Full 0.858 ± 0.004 0.833 ± 0.001 AUC MIMIC-III 0.8249 ± 0.0010 0.8364 ± 0.0011 0.8392 ± 0.0012 0.8270 ± 0.0010 0.8429 ± 0.0035 0.8390 ± 0.0011 0.8485 ± 0.0022 0.5175 ± 0.0312 0.8561 ± 0.0051 0.7734 ± 0.0030 0.8559 ± 0.0041 0.8544 ± 0.0024 0.8380 ± 0.0011 Accuracy Human Activity 0.859 ± 0.004 0.857 ± 0.002 0.860 ± 0.005 0.862 ± 0.005 0.855 ± 0.005 0.869 ± 0.007 0.815 ± 0.002 0.343 ± 0.040 0.885 ± 0.008 0.838 ± 0.004 0.870 ± 0.028 0.910 ± 0.002 0.897 ± 0.004 TPCNN (ours) Table 3: Memory and computational costs, in terms of size (number of parameters) and time per epoch (in minutes). | 2308.03210#28 | 2308.03210#30 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#30 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Model Size (parameters) mTAND-Full 1.3M 1.4M 1.6M TPCNN (ours) 350K 100K 300K Time per epoch (min) mTAND-Full 0.06 0.5 0.006 TPCNN (ours) 0.15 0.2 0.008 # PhysioNet MIMIC-III Human Activity baseline methods designed for interpolation, including RNN-VAE, L-ODE-RNN, L-ODE-ODE and mTAND- Full (i. e., mTAND encoder-decoder framework for interpolation). We mention in bold the best-performing method and underline the results for the second-performing method. We also perform tests for measuring the statistical significance of the studied methods, which leads to highlighting two distinct models that refer to the highest performances. We can observe that the best-performing method is mTAND-Full, which is closely followed by the proposed TPCNN model. The rest of the baselines show significantly worse performance compared to the proposed TPCNN, including the highly accurate in the irregular setting ODE-based method 10â 3 in terms of L-ODE-ODE. The performance of the proposed model ranges from MSE, showing a slightly improved performance as the percentage of missing observations decreases. On the other hand, mTAND-Full shows a slightly degrading performance for a smaller percentage of missing data, with RNN-VAE being the only baseline method that follows the same behavior. | 2308.03210#29 | 2308.03210#31 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#31 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Classification. We also report in Table 2 the results of the different baselines, as described in Section 4.3, and the proposed TPCNN model on classification for the labeled instances of PhysioNet, MIMIC-III and 11 â Ground Truth x â Observed data * Reconstruction sin(-) © Reconstruction exp(:) Figure 2: Reconstruction results using the proposed TPCNN model on the synthetic dataset. Three different samples of the test set are visualized. Human Activity datasets. For the first two imbalanced datasets, we use AUC as an evaluation metric and perform per-sequence binary classification, whereas, for the Human Activity dataset, we report accuracy for the task of per-time-point classification. For all datasets, we boldly mention the best-performing methods and underline the results for the second best-performing methods. Due to several non-statistically significant differences in performances, we have several methods being among the first or second best-performing. For PhysioNet and Human Activity datasets, our proposed TPCNN framework is the second-best method in terms of metrics, surpassed by the attention-based model mTAND-Full. More specifically, in PhysioNet the proposed model performs as well as the ODE variants (i. e., ODE-RNN, L-ODE-ODE) that are however significantly slow in terms of computational time, as mentioned in [27]. In Human Activity classification, TPCNN shows 1% worse than mTAND-Full. However, in the MIMIC-III classification, quite improved performance being the proposed TPCNN model lies among the third-best-performing methods, being surpassed by several baselines. In this dataset, ODE-RNN, L-ODE-ODE and mTAND-Full methods achieve the highest AUC scores, followed by the SeFT model, which however performs significantly worse in classification experiments for the other two datasets. The significant performance advantage of mTAND-Full in this task can be attributed to its design which jointly performs interpolation and classification while directly attending only to observed time points. On the other hand, the proposed model handles missing data inside the convolutional kernel of the TPC layer by applying the mean aggregator of Equation 3. The aggregation neighborhood however is constrained by the kernel size and remains fixed throughout the series length. Extending the proposed architecture to incorporate size-varying kernels could further improve the learning capabilities of the TPC layer. | 2308.03210#30 | 2308.03210#32 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#32 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | In Table 3 we provide a comparison in terms of memory and computational costs Computational cost. between the proposed TPCNN and its main competitor mTAND-Full. We report the size, i. e., the number of parameters, and the time per epoch in minutes for the two methods and the three real-world datasets. Comparisons of mTAND and previous state-of-the-art models, among which the efficient ODE-based methods, as shown in [27] have demonstrated that the former is significantly faster (i. e., approximately 100 times) than ODE-based methods that make use of an ODE solver. As we can observe in Table 3, TPCNN is as fast as mTAND-Full in terms of time cost comparison. When it comes to the size of the model, the proposed TPCNN uses significantly fewer parameters compared to mTAND-Full, while maintaining competitive performance. 350 thousand More specifically, TPCNN uses approximately some hundred thousand parameters, i. e., 100 parameters, while mTAND-Full size scales to millions of parameters, i. e., approximately 1.5 million. This comparison highlights the high efficacy of convolutions in the irregular sampling setting, which allow the training of neural networks that are significantly smaller and fast compared to the baselines. Therefore, the proposed TPCNN can easily scale to larger datasets and remains efficient even when trained with fewer parameters. | 2308.03210#31 | 2308.03210#33 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#33 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 12 â â PhysioNet _s â â MIMIC-UL Test AUC lng) et) Time Functi sin() xm) tin) Time Functions sp) {sin â +â Human Activity Ting) xn) in), 60 Time Functions } {sing Figure 3: Ablation study on different time functions for the parameterization of convolutional kernels for each dataset. Each plot captures the performance (AUC or Accuracy) for each function or combination of functions on the test set. Experiments on synthetic data. Following the line of work of [27], we reproduce their synthetic sinusoidal [0, 1]. Given dataset that consists of 1000 samples, each describing a time series of 100 time points where t 10 reference points, an RBF kernel with bandwidth 100 is used to obtain local interpolations at the 100 time steps. For each sample, 20 time points are randomly selected so as to represent an irregularly spaced series. A split of 80% and 20% extracts the respective train and test sets. We employ the encoder-decoder interpolation framework of Figure 1 (Right). Contrary to the interpolation setting for PhysioNet, we give as input the 20 irregular time steps, without the missing points, and reconstruct each observation based on the rest using TPCNN with the functions h2(x) = sin(x) (blue points) and h5(x) = exp(x) (green points). We visualize the obtained reconstructions for 3 samples of the test set in Figure 2. Each plot consists of the true values (ground truth) for a test sample, while the dark markers represent the 20 observed input data points ) (observed data), the blue markers and the green markers the 20 predicted values (reconstruction) using sin( · and exp( ) functions respectively. By employing the function h2(x) = sin(x), we are able to achieve a lower · MSE loss compared to the ones achieved with the rest of the time functions defined in Section 3.2. We should mention here that in case domain knowledge is available, it can be incorporated into the proposed TPCNN method via the employed time function, which is likely to lead to performance improvements. | 2308.03210#32 | 2308.03210#34 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#34 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Ablation study. We also present in Figure 3 an ablation study on different time functions employed for parameterizing the weights of the convolutional kernels. The performance metric (AUC or accuracy) on the test set is reported on the classification task of the real-world datasets given a different time function or combination of time functions. For all three datasets, we examine a subset of the functions described in Section 3.2. More specifically, we employ h1(x), h2(x), h3(x), h5(x) (i. e., lin( )) and ), cos( · their combination (e. g., ). We observe that different functions may ), lin( } contribute more or less to the classification performance for the given dataset. In PhysioNet, while the linear ) lead to the lowest AUC on the test set, when combined with function lin( 1%. Additionally, in MIMIC-III classification ) and cos( sin( · · cos( ) (i. e., linear function) lead ) and exp( · 4%. At the same, the combination of functions improves performance but to a reduced performance by | 2308.03210#33 | 2308.03210#35 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#35 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | ⠼ 13 ) ) when employed alone. Finally on the Human Activity dataset, cos( ) and exp( does not surpass cos( · · · ) function achieve the highest ), cos( sin( function and the combination { · · test accuracy. The linear lin( ) function again, in this case, leads to the lowest accuracy score compared to · the rest of the time functions. During training, we can observe that the linear time function followed by a standard non-linear activation (e. g., ReLU) when used for the parameterization of the convolutional kernel weights suffers from slow convergence and consequently worse performance. On the other hand, periodic time functions and the exponential function seem to more efficiently describe the time dynamics and lead to smoother training when used for parameterizing convolutions. This experiment highlights the explainability aspects of the proposed TPCNN model since it allows us to determine which time functions better describe the considered time series. Furthermore, under certain conditions, the time series could be considered as a composition of such kind of functions. | 2308.03210#34 | 2308.03210#36 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#36 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | # 5 Conclusion In this work, we carefully designed and experimentally evaluated a novel time-parameterized convolutional neural network, which incorporates learnable time functions into the weights of convolutional kernels. The proposed method generalizes well in different tasks involving irregularly sampled multivariate time series while being computationally efficient and interpretable. # References [1] E Oran Brigham. The fast Fourier transform and its applications. Prentice-Hall, Inc., 1988. [2] Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, and Yitan Li. | 2308.03210#35 | 2308.03210#37 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#37 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Brits: Bidirectional recurrent imputation for time series. Advances in neural information processing systems, 31, 2018. [3] Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, and Yan Liu. Recurrent neural networks for multivariate time series with missing values. Scientific reports, 8(1):1â 12, 2018. [4] Ricky TQ Chen, Yulia Rubanova, Jesse Bettencourt, and David Duvenaud. | 2308.03210#36 | 2308.03210#38 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#38 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Neural ordinary differential equations. In Advances on Neural Information Processing Systems, pages 6572â 6583, 2018. [5] Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555, 2014. [6] Edward De Brouwer, Jaak Simm, Adam Arany, and Yves Moreau. Gru-ode-bayes: Continuous modeling of sporadically-observed time series. Advances in neural information processing systems, 32, 2019. [7] Jan G De Gooijer and Rob J Hyndman. 25 years of time series forecasting. International Journal of Forecasting, 22(3):443â 473, 2006. [8] Crist´obal Esteban, Stephanie L Hyland, and Gunnar R¨atsch. | 2308.03210#37 | 2308.03210#39 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#39 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Real-valued (medical) time series generation with recurrent conditional gans. arXiv preprint arXiv:1706.02633, 2017. [9] Joseph Futoma, Sanjay Hariharan, and Katherine Heller. Learning to detect sepsis with a multitask gaussian process rnn classifier. In International conference on machine learning, pages 1174â 1182. PMLR, 2017. [10] Sepp Hochreiter and J¨urgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735â 1780, 1997. [11] Max Horn, Michael Moor, Christian Bock, Bastian Rieck, and Karsten Borgwardt. | 2308.03210#38 | 2308.03210#40 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#40 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Set functions for time series. In International Conference on Machine Learning, pages 4353â 4363. PMLR, 2020. 14 [12] Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, and Pierre-Alain Muller. Deep learning for time series classification: a review. Data mining and knowledge discovery, 33(4):917â 963, 2019. [13] Alistair EW Johnson, Tom J Pollard, Lu Shen, Li-wei H Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. Mimic-iii, a freely accessible critical care database. Scientific data, 3(1):1â | 2308.03210#39 | 2308.03210#41 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#41 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 9, 2016. [14] Patrick Kidger, James Morrill, James Foster, and Terry Lyons. Neural controlled differential equations for irregular time series. Advances in Neural Information Processing Systems, 33:6696â 6707, 2020. [15] Yann LeCun, L´eon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278â 2324, 1998. [16] Yonghong Luo, Xiangrui Cai, Ying Zhang, Jun Xu, et al. | 2308.03210#40 | 2308.03210#42 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#42 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Multivariate time series imputation with generative adversarial networks. Advances in neural information processing systems, 31, 2018. [17] Hongyuan Mei and Jason M Eisner. The neural hawkes process: A neurally self-modulating multivariate point process. Advances in neural information processing systems, 30, 2017. [18] Michael C Mozer, Denis Kazakov, and Robert V Lindsey. Discrete event, continuous time rnns. arXiv preprint arXiv:1710.04110, 2017. [19] Daniel Neil, Michael Pfeiffer, and Shih-Chii Liu. Phased lstm: Accelerating recurrent network training for long or event-based sequences. Advances in neural information processing systems, 29, 2016. | 2308.03210#41 | 2308.03210#43 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#43 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | [20] Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. Deepsdf: Learning continuous signed distance functions for shape representation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 165â 174, 2019. [21] Trang Pham, Truyen Tran, Dinh Phung, and Svetha Venkatesh. Predicting healthcare trajectories from medical records: A deep learning approach. Journal of biomedical informatics, 69:218â 229, 2017. [22] Alvin Rajkomar, Eyal Oren, Kai Chen, Andrew M Dai, Nissan Hajaj, Michaela Hardt, Peter J Liu, Xiaobing Liu, Jake Marcus, Mimi Sun, et al. Scalable and accurate deep learning with electronic health records. NPJ digital medicine, 1(1):1â 10, 2018. [23] David W Romero, Anna Kuzina, Erik J Bekkers, Jakub M Tomczak, and Mark Hoogendoorn. Ckconv: Continuous kernel convolution for sequential data. arXiv preprint arXiv:2102.02611, 2021. [24] Yulia Rubanova, Ricky TQ Chen, and David K Duvenaud. Latent ordinary differential equations for irregularly-sampled time series. Advances in neural information processing systems, 32, 2019. | 2308.03210#42 | 2308.03210#44 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#44 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | [25] Kristof Sch¨utt, Pieter-Jan Kindermans, Huziel Enoc Sauceda Felix, Stefan Chmiela, Alexandre Tkatchenko, and Klaus-Robert M¨uller. Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. Advances in neural information processing systems, 30, 2017. [26] Satya Narayan Shukla and Benjamin M Marlin. Interpolation-prediction networks for irregularly sampled time series. arXiv preprint arXiv:1909.07782, 2019. [27] Satya Narayan Shukla and Benjamin M Marlin. Multi-time attention networks for irregularly sampled time series. arXiv preprint arXiv:2101.10318, 2021. [28] Ikaro Silva, George Moody, Daniel J Scott, Leo A Celi, and Roger G Mark. | 2308.03210#43 | 2308.03210#45 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#45 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Predicting in-hospital mortality of icu patients: The physionet/computing in cardiology challenge 2012. In 2012 Computing in Cardiology, pages 245â 248. IEEE, 2012. 15 [29] Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. Implicit neural representations with periodic activation functions. Advances in Neural Information Processing Systems, 33:7462â 7473, 2020. [30] Huan Song, Deepta Rajan, Jayaraman Thiagarajan, and Andreas Spanias. | 2308.03210#44 | 2308.03210#46 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#46 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Attend and diagnose: Clinical time series analysis using attention models. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018. [31] Qingxiong Tan, Mang Ye, Baoyao Yang, Siqi Liu, Andy Jinhua Ma, Terry Cheuk-Fung Yip, Grace Lai-Hung Wong, and PongChi Yuen. Data-gru: Dual-attention time-aware gated recurrent unit for irregular multivariate time series. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 930â | 2308.03210#45 | 2308.03210#47 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#47 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | 937, 2020. 32 Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017. [33] Shenlong Wang, Simon Suo, Wei-Chiu Ma, Andrei Pokrovsky, and Raquel Urtasun. Deep parametric continuous convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2589â 2597, 2018. [34] Paul J Werbos. | 2308.03210#46 | 2308.03210#48 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#48 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | Backpropagation through time: what it does and how to do it. Proceedings of the IEEE, 78(10):1550â 1560, 1990. [35] Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. Self-attention with functional time representation learning. Advances in neural information processing systems, 32, 2019. [36] Jinsung Yoon, William R Zame, and Mihaela van der Schaar. Estimating missing data in temporal data streams using multi-directional recurrent neural networks. IEEE Transactions on Biomedical Engineering, 66(5):1477â 1490, 2018. | 2308.03210#47 | 2308.03210#49 | 2308.03210 | [
"1710.04110"
]
|
2308.03210#49 | Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series | [37] Yuan Zhang. Attain: Attention-based time-aware lstm networks for disease progression modeling. In In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-2019), pp. 4369-4375, Macao, China., 2019. 16 | 2308.03210#48 | 2308.03210 | [
"1710.04110"
]
|
|
2308.03022#0 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | 3 2 0 2 g u A 6 ] C H . s c [ 1 v 2 2 0 3 0 . 8 0 3 2 : v i X r a 2023 11th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) # SAPIEN: Affective Virtual Agents Powered by Large Language Models* Masum Hasanâ , Cengiz Ozelâ , Sammy Potterâ ¡ and Ehsan Hoque§ Department of Computer Science, University of Rochester Rochester, NY, United States Email: {â m.hasan@, â cozel@cs., â ¡spotter14@u., §mehoque@cs.} rochester.edu Abstractâ | 2308.03022#1 | 2308.03022 | [
"1703.10135"
]
|
|
2308.03022#1 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | In this demo paper, we introduce SAPIEN, a plat- form for high-fidelity virtual agents driven by large language models that can hold open domain conversations with users in 13 different languages, and display emotions through facial expressions and voice. The platform allows users to customize their virtual agentâ s personality, background, and conversation premise, thus providing a rich, immersive interaction experience. Furthermore, after the virtual meeting, the user can choose to get the conversation analyzed and receive actionable feedback on their communication skills. This paper illustrates an overview of the platform and discusses the various application domains of this technology, ranging from entertainment to mental health, com- munication training, language learning, education, healthcare, and beyond. Additionally, we consider the ethical implications of such realistic virtual agent representations and the potential challenges in ensuring responsible use. | 2308.03022#0 | 2308.03022#2 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#2 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | 03:21/10:00 SAPIEN Fig. 1. Face-to-face video call interaction with SAPIENTM Virtual Agent Index Termsâ Virtual Avatars, Virtual Agents, Affective AI, Large Language Models # I. INTRODUCTION Allowing a user to define the traits and characteristics of a virtual agent, carrying a dynamic conversation, and receiving automated feedback has been an open-ended research problem for many years [1]. The rapid advancement of Large Language Models (LLMs) in recent years has enabled possibilities in designing user experiences that didnâ | 2308.03022#1 | 2308.03022#3 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#3 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | t exist before [2]â [4]. In this demo, we present Synthetic Anthropomorphic Personal Interaction ENgine (SAPIEN), a platform for LLM-powered high-fidelity virtual agents that can engage in real-time open- domain conversations, while also expressing emotions through voice and facial expressions. One of the notable features of SAPIEN is its extensive range of customization options, allowing users to engage in immersive and meaningful interactions. Users can choose from a wide range of virtual agent avatars that reflect a diverse array of ages, gender, and ethnicities. Going further, users can select the desired personality, background, and conversational context of a virtual agent, creating an experience tailored to their specific needs or preferences. | 2308.03022#2 | 2308.03022#4 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#4 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | SAPIEN leverages state-of-the-art models in Speech-to-Text [5], [6], Text-to-Speech [7]â [9], and large language modeling [2], [4], [10]â [14]. The virtual agents fluently speak thirteen different languages and counting, making it accessible across a global user base. Upon finishing a video call with the virtual agents, a user can choose to get their conversation analyzed for personalized feedback. The system provides AI-generated feedback to the user based on the userâ | 2308.03022#3 | 2308.03022#5 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#5 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | s goal. The user can decide the topic of the feedback to suit their learning goal and repeat the conver- sation until the learning goal is met. The inherent flexibility of the virtual agent persona and the feedback could make it potentially applicable to a myriad of applications, including communication training, language learning, and professional applications like healthcare, sales, and leadership training. With the rising technical capabilities of LLMs, there is expected to be a drastic shift in the labor market in the coming years [15]. According to recent studies [15], the importance of the job market is going to shift from hard technical skills to soft â | 2308.03022#4 | 2308.03022#6 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#6 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | humanâ skills. In this changing landscape, SAPIEN can help people adapt and cope, by helping them cultivate human skills with the help of AI. Once a virtual agent is selected and its traits are defined, users can begin a real-time video call interaction with it. With the help of the large language model, the virtual agents dynamically adjust their emotional state, vocal, and facial expressions, showcasing a spectrum of seven basic emotions. NSF and NSF REU IIS-1750380, Seedling from Goergen Institute for Data Science (GIDS), and Gordon and Moore Foundation. # II. SYSTEM DESCRIPTION The overall working of SAPIEN Virtual Agents, referred to as â | 2308.03022#5 | 2308.03022#7 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#7 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Botâ for simplicity, is represented in Figure 2. The SAPIEN system is initialized when a userâ s speech utterance is captured and transmitted to our back-end server for processing. This utterance is transcribed into text by a high-precision Speech # 979-8-3503-2745-8/23/$31.00 ©2023 IEEE Front End (Client Side) 3DGame Engine | ® Bot Response Audio 7 K Bot Response au Audio User Utterance Blendshapes: â Y ' Autoregressive ' Lm Back End (Server Side) Large Language Model Previous History ot) User defined parameters Facial Expression Motion Capture Database _â Bot Response Text Text to Speech Systen User Utterance Text Audio : a Speech to Text : | 2308.03022#6 | 2308.03022#8 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#8 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Fig. 2. A single turn conversation flow in SAPIEN. User utterance is transcribed and sent to LLM. The LLM response is spoken out by the virtual agent. to Text (STT) model [5], [6], [16], [17] and subsequently processed by an autoregressive Large Language Model (LLM) fine-tuned for instruction following [3], [4], [10]â [14], [18]. The LLM is conditioned on user-defined parameters like personality traits, conversation premise, user information, and previous conversation history. To prevent inappropriate or of- fensive behavior, the LLM also adheres to system guardrails. A notable aspect of the LLM is also predicting the virtual agentâ | 2308.03022#7 | 2308.03022#9 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#9 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | s emotional state. Conditioning on the user-defined parameters, system guardrails, and previous conversation history, the LLM is instructed to generate the botâ s response, alongside the appropriate emotional state of the bot from the following list: Neutral, Happy, Sad, Angry, Surprised, Afraid, and Disgusted. This emotional state, along with the text response, is used to generate an audio file of the botâ s response using a Text to Speech (TTS) model. Concurrently, the emotional state triggers the selection of a corresponding facial expression from our pre-recorded motion capture database. This facial expression data, in the form of blendshapes, is passed to a 3D game engine to animate the virtual agent. The resultant animation and generated audio are synchro- nized, forming a coherent, visually expressive response from the virtual agent. This combined output is streamed to the userâ s web browser in near real-time, allowing for an immer- sive experience close to an actual video call. | 2308.03022#8 | 2308.03022#10 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#10 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | munication practice tool for people with social anxiety or neurodiversity [19], [20], public speaking [21], job interviews [22], helping elderly with social skills [23], and even speed dating [24]. It also has an excellent potential for professional applications. Such as training doctors in bedside manners or delivering difficult news to their patients [25], personalized training for leadership, business negotiation, sales, marketing, etc. The multilingual ability makes the platform a powerful tool for language learners. Furthermore, the non-judgemental, low stake, repeatable conversations with virtual agents make the platform a helpful tool for anyone to roleplay any difficult interpersonal scenario in a personal or professional setup. | 2308.03022#9 | 2308.03022#11 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#11 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | # IV. THE DEMO Our platform is hosted in the cloud and accessible from any part of the world. During the conference demo, we wish to have the visitors live interact with SAPIEN virtual agents in a variety of interesting scenarios and receive immediate feedback on their communication skills. We will also prepare some pre-recorded user interaction videos to demonstrate any rare or difficult cases or as a backup for technical failures. # ETHICAL IMPACT STATEMENT Once the conversation is over, the user can opt-in to receive feedback on their conversation. An LLM is instructed to analyze the conversation transcript based on the userâ s goal, identify strengths and weaknesses on the userâ s communica- tion skill, and generate actionable feedback for the user. | 2308.03022#10 | 2308.03022#12 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#12 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | # III. APPLICATIONS The customizability of the conversation scenario, dynamic dialogues, and the feedback system combined make SAPIEN uniquely suitable for a variety of communication training purposes. For example, the system can be used as a com- SAPIEN is designed to augment and enrich our capacity for communication, empathy, and understanding, but not substi- tute human connections. To safeguard against potential emo- tional dependencies on the system, SAPIEN does not retain the memory of previous interactions, and the conversations are limited to a 10 minutes window with a warning at the 8- minute mark. To prevent the practice of bullying or abusive behaviors using our system, we enabled our virtual agents to end the video call if the user repeatedly displays aggressive or offensive behavior. We are continuously investigating more safety and ethical issues regarding the use of the system. | 2308.03022#11 | 2308.03022#13 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#13 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | # REFERENCES [1] M. E. Hoque and R. W. Picard, â Rich nonverbal sensing technology for automated social skills training,â Computer, vol. 47, no. 4, pp. 28â 35, 2014. [2] OpenAI, â Introducing chatgpt,â https://openai.com/blog/chatgpt, (Ac- cessed on 06/22/2023). [3] â Anthropic â introducing claude,â https://www.anthropic.com/index/ introducing-claude, (Accessed on 06/22/2023). | 2308.03022#12 | 2308.03022#14 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#14 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | [4] G. AI, â An important next step on our ai journey,â 2023. [Online]. Avail- able: https://blog.google/technology/ai/bard-google-ai-search-updates/ automatic Sig- speech nal [On- line]. Available: https://www.microsoft.com/en-us/research/publication/ recent-advances-in-end-to-end-automatic-speech-recognition/ [6] W. Xiong, L. Wu, F. Alleva, J. Droppo, X. Huang, and A. | 2308.03022#13 | 2308.03022#15 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#15 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Stolcke, â The microsoft 2017 conversational speech recognition system,â in 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). [7] Y. Wang, R. Skerry-Ryan, D. Stanton, Y. Wu, R. J. Weiss, N. Jaitly, Z. Yang, Y. Xiao, Z. Chen, S. Bengio et al., â Tacotron: Towards end- to-end speech synthesis,â | 2308.03022#14 | 2308.03022#16 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#16 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | arXiv preprint arXiv:1703.10135, 2017. [8] R. Luo, X. Tan, R. Wang, T. Qin, J. Li, S. Zhao, E. Chen, and T.-Y. Liu, â Lightspeech: Lightweight and fast text to speech with neural architec- ture search,â in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021, pp. 5699â 5703. [9] S.-g. Lee, H. Kim, C. Shin, X. Tan, C. Liu, Q. Meng, T. Qin, W. Chen, S. Yoon, and T.-Y. Liu, â | 2308.03022#15 | 2308.03022#17 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#17 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Priorgrad: Improving conditional denoising diffusion models with data-driven adaptive prior,â ICLR, 2022. [10] R. Taori, I. Gulrajani, T. Zhang, Y. Dubois, X. Li, C. Guestrin, P. Liang, and T. B. Hashimoto, â Stanford alpaca: An instruction-following llama model,â https://github.com/tatsu-lab/stanford alpaca, 2023. [11] T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., â | 2308.03022#16 | 2308.03022#18 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#18 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Language mod- els are few-shot learners,â Advances in neural information processing systems, vol. 33, pp. 1877â 1901, 2020. [12] OpenAI, â Gpt-4 technical report,â 2023. [13] L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray et al., â | 2308.03022#17 | 2308.03022#19 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#19 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Training language models to follow instructions with human feedback,â Advances in Neural Information Processing Systems, vol. 35, pp. 27 730â 27 744, 2022. [14] A. K¨opf, Y. Kilcher, D. von R¨utte, S. Anagnostidis, Z.-R. Tam, K. Stevens, A. Barhoum, N. M. Duc, O. Stanley, R. Nagyfi et al., â Ope- nassistant conversationsâ democratizing large language model align- ment,â | 2308.03022#18 | 2308.03022#20 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#20 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | arXiv preprint arXiv:2304.07327, 2023. [15] T. Eloundou, S. Manning, P. Mishkin, and D. Rock, â Gpts are gpts: An early look at the labor market impact potential of large language models,â arXiv preprint arXiv:2303.10130, 2023. [16] Y. Leng, X. Tan, L. Zhu, J. Xu, R. Luo, L. Liu, T. Qin, X. Li, E. Lin, and T.-Y. Liu, â | 2308.03022#19 | 2308.03022#21 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#21 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Fastcorrect: Fast error correction with edit alignment for automatic speech recognition,â Advances in Neural Information Processing Systems, vol. 34, pp. 21 708â 21 719, 2021. [17] W. Hou, J. Wang, X. Tan, T. Qin, and T. Shinozaki, â Cross-domain speech recognition with unsupervised character-level distribution match- ing,â INTERSPEECH, 2021. [18] W.-L. Chiang, Z. Li, Z. Lin, Y. Sheng, Z. Wu, H. Zhang, I. | 2308.03022#20 | 2308.03022#22 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#22 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Stoica, impressing gpt- [Online]. Available: [19] M. R. Ali, S. Z. Razavi, R. Langevin, A. Al Mamun, B. Kane, R. Rawassizadeh, L. K. Schubert, and E. Hoque, â A virtual teens with autism spectrum disorder: conversational Experimental results and design lessons,â in Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents, ser. IVA â 20. | 2308.03022#21 | 2308.03022#23 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#23 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | New York, NY, USA: Association for Computing Machinery, 2020. [Online]. Available: https://doi.org/10.1145/3383652.3423900 [20] S. Z. Razavi, M. R. Ali, T. H. Smith, L. K. Schubert, and M. E. Hoque, â The lissa virtual human and asd teens: An overview of initial experiments,â in Intelligent Virtual Agents, D. | 2308.03022#22 | 2308.03022#24 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#24 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Traum, W. Swartout, P. Khooshabeh, S. Kopp, S. Scherer, and A. Leuski, Eds. Cham: Springer International Publishing, 2016, pp. 460â 463. [21] M. Fung, Y. Jin, R. Zhao, and M. E. Hoque, â Roc speak: Semi- automated personalized feedback on nonverbal behavior from recorded videos,â | 2308.03022#23 | 2308.03022#25 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#25 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | in Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing, ser. UbiComp â 15. New York, NY, USA: Association for Computing Machinery, 2015, p. 1167â 1178. [Online]. Available: https://doi.org/10.1145/2750858.2804265 [22] M. E. Hoque, M. Courgeon, J.-C. Martin, B. Mutlu, and R. W. Picard, â Mach: My automated conversation coach,â | 2308.03022#24 | 2308.03022#26 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#26 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | in Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, ser. UbiComp â 13. New York, NY, USA: Association for Computing Machinery, 2013, p. 697â 706. [Online]. Available: https://doi.org/10.1145/2493432.2493502 [23] S. Z. Razavi, L. K. Schubert, K. van Orden, M. R. Ali, B. | 2308.03022#25 | 2308.03022#27 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#27 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | Kane, interacting in multiple topics,â ACM Trans. jul 2022. [Online]. Available: [24] M. R. Ali, D. Crasta, L. Jin, A. Baretto, J. Pachter, R. D. Rogge, and M. E. Hoque, â Lissa â live interactive social skill assistance,â in 2015 International Conference on Affective Computing and Intelligent Interaction (ACII), 2015, pp. 173â | 2308.03022#26 | 2308.03022#28 | 2308.03022 | [
"1703.10135"
]
|
2308.03022#28 | SAPIEN: Affective Virtual Agents Powered by Large Language Models | 179. [25] M. R. Ali, T. Sen, B. Kane, S. Bose, T. M. Carroll, R. Epstein, L. Schubert, and E. Hoque, â Novel computational linguistic measures, dialogue system and the development of sophie: Standardized online for healthcare interaction education,â IEEE Trans. Affect. patient Comput., vol. 14, no. 1, p. 223â 235, jan 2023. [Online]. Available: https://doi.org/10.1109/TAFFC.2021.3054717 | 2308.03022#27 | 2308.03022 | [
"1703.10135"
]
|
|
2308.02773#0 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | 3 2 0 2 g u A 5 ] L C . s c [ 1 v 3 7 7 2 0 . 8 0 3 2 : v i X r a EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education Yuhao Dan1â , Zhikai Lei1â , Yiyang Gu1â , Yong Li1, Jianghao Yin1, Jiaju Lin1, Linhao Ye1, Zhiyan Tie1, Yougen Zhou1, Yilei Wang2, Aimin Zhou1,2, Ze Zhou4 Qin Chen1â , Jie Zhou1â , Liang He1 , Xipeng Qiu3 1 School of Computer Science and Technology, East China Normal University, Shanghai, China 2 Institute of AI for Education, ECNU, Shanghai, China 3 School of Computer Science, Fudan University, Shanghai, China 4 ZhuQingTing Data Technology (Zhejiang) Co., Ltd., Zhejiang, China # Abstract sonalized, comprehensive, and timely support to teachers, students, and parents. EduChat1 is a large-scale language model (LLM)-based chatbot system in the education domain. Its goal is to support personalized, fair, and compassionate intelligent education, serv- ing teachers, students, and parents. Guided by theories from psychology and education, it fur- ther strengthens educational functions such as open question answering, essay assessment, So- cratic teaching, and emotional support based on the existing basic LLMs. Particularly, we learn domain-specific knowledge by pre-training on the educational corpus and stimulate various skills with tool use by fine-tuning on designed system prompts and instructions. Currently, EduChat is available online as an open-source project, with its code, data, and model parame- ters available on platforms (e.g., GitHub2, Hug- ging Face3). We also prepare a demonstration of its capabilities online4. This initiative aims to promote research and applications of LLMs for intelligent education. | 2308.02773#1 | 2308.02773 | [
"2302.13971"
]
|
|
2308.02773#1 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | # Introduction Recently, large-scale language models (LLMs), such as ChatGPT (Schulman et al., 2022), LLaMa (Touvron et al., 2023a), have achieved great suc- cess in the field of natural language processing (Zhou et al., 2023b). LLMs obtained the ability of reasoning, long-range context modeling, and task generalization by training on large-scale tex- tual corpus with some strategies, such as code pre- training (Chen et al., 2021), instruction tuning (Wei et al., 2022), and reinforcement learning from hu- man feedback (RLHF) (Stiennon et al., 2020). With the advent of LLMs, they have the potential to rev- olutionize intelligent education by providing per- | 2308.02773#0 | 2308.02773#2 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#2 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | â â Equal contribution. â â Corresponding author. 1https://www.educhat.top/ 2https://github.com/icalk-nlp/EduChat 3https://huggingface.co/ecnu-icalk 4https://vimeo.com/851004454?share=copy However, there are several challenges of apply- ing LLMs into education domain. One challenge (C1) is that there is still a gap between the LLMs and the educational expert since LLMs are pre- trained on the general corpus, which lack sufficient educational knowledge and can not align well with real scenarios (e.g., essay assessment). The other challenge (C2) is that the knowledge in the field of education is updating, while LLMs can not learn up-to-date knowledge due to the training mecha- nism. Moreover, LLMs suffer from the hallucina- tion problem, and may generate responses that are not truthful. To address these problems, we propose EduChat, an LLM-based chatbot system for intelligent educa- tion. For C1, we pre-train LLMs on a large number of educational books (e.g., psychology, ancient po- etry) and 4 million cleaned diverse instructions to learn the fundamental knowledge. Then, we fine- tune the model on 500 thousand high-quality cus- tomized instructions to activate education-specific functions (e.g., essay assessment, Socratic teach- ing and emotional support), by aligning with the feedbacks from psychology experts and frontline teachers. For C2, we explore a retrieval-augmented technology, which enables LLMs to automatically judge the helpfulness of the retrieved information, and generate the response based on the relevant in- formation and knowledge stored in LLMs. In this way, our EduChat can access the latest information from the internet, ensuring that the responses are accurate and credible. As an open-source project, EduChat improves the performance of education- specific functions while maintaining comparable foundational capabilities to other large-scale mod- els with equivalent parameter size. | 2308.02773#1 | 2308.02773#3 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#3 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | The main con- tributions are as follows: â ¢ We explore the potential of incorporating theories of psychology and education into LLMs, which sheds light on how to adapt general LLMs to specific domains; â ¢ Diverse system prompts and instructions are de- signed to control the tool use and stimulate differ- ent skills, which alleviates the problem of hallu- cination and is more applicable in real education scenarios; â ¢ We develop and release the EduChat system with various educational functions, thus developers and researchers can help speed up the research and applications of intelligent education. # 2 Related Work Recently, LLMs like ChatGPT (Schulman et al., 2022), ChatGLM (Du et al., 2022), and LLaMA2- Chat (Touvron et al., 2023b) have emerged as a breakthrough technology in natural language pro- cessing, achieving strong performance on language generation and understanding through pre-training on massive text and instruction tuning. While LLMs demonstrate impressive capabili- ties in general domains, their lack of subject-matter expertise becomes apparent when applied to spe- cialized verticals. For instance, we can find spe- cialized language models catering to various do- mains, such as ChatDoctor (Li et al., 2023) and HuaTuoGPT (Zhang et al., 2023b) in healthcare, FinGPT (Yang et al., 2023) in finance, and Chat- Law (Cui et al., 2023) in the legal domain. These niche fields inherently necessitate models to pos- sess comprehensive domain knowledge to address relevant queries, especially when assisting real users in practical scenarios. In education, Baladn et al. (2023) tune open-source LLMs for generating better teacher responses in BEA 2023 Shared Task (Tack et al., 2023). But challenges still exist, such as the lack of domain knowledge in general LLMs and the necessity for them to align with educational abilities (e.g., essay assessment, emotional support, and Socratic teaching). EduChat is pre-trained on a diverse education corpus to ensure the alignment of EduChat with educational abilities. # 3 Core Functions of EduChat | 2308.02773#2 | 2308.02773#4 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#4 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | Retrieval-Augmented Open Question Answer- ing (QA) The education domain demands high accuracy and real-time updates regarding knowl- edge and related policies. However, existing gener- ative LLMs suffer from issues like fabricating infor- mation and lagging behind in knowledge updates. To address this, we explore retrieval-augmented open QA methods. By utilizing real-time updated corpora from the internet as an external knowledge source, we enable LLMs to autonomously assess the relevance of retrieved information to answer a given question and decide which information to incorporate for generating responses. Through extensive experimental analysis, we discover that our model exhibits significant advantages over gen- eral LLMs in terms of eliminating fabrications and maintaining up-to-date knowledge. Fine-grained Essay Assessment In essay assess- ment, teachers meticulously annotate grammar er- rors, provide scores, and offer feedback on standout sentences. Existing language models often have coarse granularity in grading, limiting studentsâ writing skill improvement. Our research focuses on more fine-grained and comprehensive essay assess- ment. Combining frontline teaching profession- alsâ expertise, we provide overall scores, aspect- level ratings, and detailed comments on content, expression, paragraph, and overall evaluation. Our model can identify standout sentences, highlight- ing strengths and areas for improvement, enabling personalized guidance for studentsâ essay writing skills. This ensures timely and professional support in all aspects of writing. Socratic Teaching We focus on developing So- cratic teaching capabilities in LLMs rather than providing direct answers to students. We adopt the Socratic dialogue method, engaging in multi-step question-and-answer interactions to encourage in- dependent thinking. By stimulating discussions, debates, evaluations, and analyses, we aim to fos- ter advanced cognitive skills and cultivate studentsâ autonomy in learning. Our ultimate goal is to en- hance critical thinking and innovation abilities to their fullest extent. Psychology-based Emotional Support Adoles- cents and children face more severe psychological pressures due to their immature cognitive devel- opment. Whereas, current LLMs usually provide generic advice, which can not well fit the specific emotional problem. To address this, we develop a psychological inquiry framework based on emotion psychology, such as Rational Emotive Behavior Therapy (REBT) and the ABC theory (Ellis, 1991). Our fine-tuned model can simulate a psycholog- ical counselor, providing personalized diagnoses and emotional support for users. | 2308.02773#3 | 2308.02773#5 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#5 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | EduChat fosters a deeper understanding of usersâ emotional states and offers accurate and professional assistance. # 4 Data Construction # 4.1 Pre-training Data Textbooks Data In our research, we gather a vast amount of educational textbook and online question bank data from Chinese middle and high school exams for pre-training. Additionally, we en- rich our model with over 70,000 Chinese poetries, providing detailed information on authors, back- grounds, and poetry appreciation to enhance its poetry creation and appreciation capabilities. To facilitate empathetic emotional support dialogues, we carefully select 60 famous works from hun- dreds of psychology books. These selected books belong to two main categories. The first category consists of 15 branches of psychological theory, in- cluding developmental and educational psychology, social psychology, behavioral psychology, counsel- ing psychology and others. The second category contains various psychological practices, which of- fer practical cases of psychological consultation and emotional support dialogues. By incorporat- ing the diverse fundamental data into pre-training, our model gains a deeper understanding of educa- tion and psychology, enabling it to generate more helpful responses. Fundamental Instruction Data To achieve a more natural human-computer interaction, we col- lect a large volume of bilingual instruct tuning data from reputable open-source repositories like Al- paca5, BELLE (Ji et al., 2023), GPT4All6, Open- Assistant7, FLANCoT8, and Firefly9. The data spans various task types, enabling our models to acquire foundational instruction following capabil- ities for diverse instruction types. In addition, we source high-quality multi-turn dialogue data from MOSS (Sun et al., 2023), BELLE (Ji et al., 2023), COIG (Zhang et al., 2023a), LIMA (Zhou et al., 2023a), and ShareGPT10. This data covers various dialogue contexts, including role-playing, creative writing, and code-related discussions, ensuring our modelsâ competence in engaging and sustaining meaningful multi-turn conversations. # 5https://github.com/tatsu-lab/stanford_alpaca 6https://github.com/nomic-ai/gpt4all 7https://github.com/LAION-AI/Open-Assistant 8https://huggingface.co/datasets/lucasmccabe- | 2308.02773#4 | 2308.02773#6 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#6 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | # lmi/FLAN_CoT_alpaca_style # 9https://github.com/yangjianxin1/Firefly 10https://huggingface.co/datasets/gozfarb/ShareGPT_ Vicuna_unfiltered me Essay Assessment â m= _Emotional Support â mm Retrieval-Augmented Open QA Socratic Teaching 29.4% Figure 1: Distribution of educational data. 4.2 Fine-tuning Data To enhance the capability of education, we con- struct the Educational Instruction Data for fine- tuning, which covers retrieval-augmented open QA, emotional support, Socratic teaching and essay as- sessment. The distribution is shown in Figure 1. Retrieval-Augmented Open QA Data To ad- dress hallucination and timely knowledge issues in Open QA, we design a retrieval-augmented open QA technique. We sample high-quality data through ChatGPT scoring in relevant Open QA and Subject QA datasets. To tackle irrelevant retrieved content, we introduce self-checking. ChatGPT as- sesses whether the retrieval content helps answer the question and then generates the answer using an self-check, incorporating the useful retrieval con- tent and questions. To maintain data quality, we manually verify the data during this process. Emotional Support Data To overcome the scarcity of Chinese emotional support dialogue data, we adopt a translation and expansion ap- proach. We translate the widely-used English emo- tional support dataset, ESConv (Liu et al., 2021), into Chinese as ESConv-zh. After manual review and cleaning, we simulate multi-agent dialogues based on various patient scenarios within ESConv- zh and also collect real-life Chinese psychological counseling consultation data, incorporating patient information and diagnosis results. By training our models on diverse datasets, we empower them to provide robust emotional support and act as com- passionate counselors during consultations. Socratic Teaching Data Teachers play a key role in guiding and encouraging heuristic exploration rather than just providing answers. To support this, we generate dialogues simulating the Socratic teaching method by incorporating multi-step Q&A involving counter-questions, challenges, and in- quiries. These dialogues are manually evaluated | 2308.02773#5 | 2308.02773#7 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#7 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | Io eee eee eee ee ' x Web Search General ' ' if > aa S L 1 my lam an Al assistant named EduChat. | | Tools | ©. & ) f Psychol. i i aH alculators aaa sychology Han 1 c yet a it 1 | Personal EduChatis a conversational language | Q Skill tu ! | Profile model developed by ECNU. Self-check Socrates : ' 1 Ability Pre-training Textbooks #TEXT Textbooks Fundamental Instruction through the dawning beams. | 2308.02773#6 | 2308.02773#8 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#8 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | By the window <TITLE> Bamboo Shadows Amidst Lingering Snow <POETRY> A speck of vanishing snow remains, A lone maon amidst bamboo shades i wanes. In the clear night, ts brillance gleams, Cold air ingers Fine-tuning Essay Assessment wee Meee Fundamental Instruction INSTRUCTION {A Itean replicate in human blood plasma, #RESPONSE family Hepadnaviidae, a hepattrople DNA, ' 1 1 1 ' Educational t Instruction 1 1 1 1 â The correct statement about Hepatitis B viru is (). B. It cannot parasitze in respiratory mucosal cell C. its nucleic acd contains 5 nitrogenous bases. 1. its protein i synthesized by its own ribosomes. â Answer is B. Hepatitis B virus (HBV) belongs tothe Knowledge > a Socratic ' ' Emotional ' & @® Eauchat iS oman | + C.China â D. United Kingdom â f t {| @:tn which country will the 1 | 2024 Olympic Games beheld? |â > | Search =| _» a Franceâ B. Unied States Engine f \ (1) Paris, France; Hamburg, Germany; Budapest, Hungary; \ iy dnb kia et cone > Useless X # Prefix ! Chest 22¢ Seer Opes Bee and ()i8 ! Symes wl ake place Yom uly 25 fo gus 1 useless, Result (2) i CEE He usetuly | py atuneui, corm || | '@) On September 13, 2017, during the 131st international lise the Information ' â Olymple Commit (OC) Session held in Lima, Pen, > Useless X | from the Result (2) ' Portus sav ste hs iy rt en ' x js Figure 2: The overall framework of EduChat. for accuracy, fluency, and progression from easy to complex questions. Integrating this dataset into training equips our model with a strong capability in Socratic teaching, distinguishing it from other LLMs that only offer direct answers. Essay Assessment Data The lack of timely and detailed feedback often hinders studentsâ writing improvement. To tackle this issue, we create a high-quality essay assessment dataset. | 2308.02773#7 | 2308.02773#9 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#9 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | Initially, we collect essays and employ ChatGPT to evaluate them in terms of content, expression, and overall quality. To ensure data quality, we invite pedagogi- cal experts to manually curate the comments. This dataset empowers EduChat with the ability to pro- vide students with high-quality feedback, aiding in the enhancement of their writing skills. GPU acceleration, speeding up the process. # 5 EduChat EduChat is an LLM designed for the education do- main (Figure 2). We first pre-train on large-scale education corpus (e.g., textbooks, instructions for foundational tasks) to learn the domain-specific and foundational knowledge. We then learn the pedagogical skills by fine-tuning EduChat on task- specific instruction datasets. Moreover, we lever- age online retrieval to enhance the accuracy and timeliness of knowledge in its responses. To con- trol skills, we design various system prompts to unlock different scenes with tool usage. # 5.1 Training Procedure of EduChat # 4.3 Data Preprocessing To enhance data quality, we conduct semantic-level deduplication on the dataset. Using the sentence- transformers model (Reimers and Gurevych, 2019), we obtain sentence embeddings for each data point and calculate cosine similarity between all pairs of embeddings. For similarities exceeding a threshold of 0.7, we remove one of the duplicates. We im- plement the similarity calculation using CUDA for | 2308.02773#8 | 2308.02773#10 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#10 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | The training of EduChat is mainly divided into two stages: fundamental capabilities acquisition and educational skills acquisition. In the first stage, we pre-train the model on educational books and Q&A pairs (detailed in Section 4.1) to equip it with foundational knowledge across disciplines. Besides, large-scale instruction tuning and open- domain dialogue datasets are also incorporated to enable basic instruction following ability and dia- logue ability (detailed in Section 4.2). In the second @ Open QA + New Topic Topic 1 2024/07/90 1421.96 Topic 2 new Chat Please introduce East China Normal University t4 East China Normal University (ECNU) is a comprehensive public research university located in Shanghai, China. it was founded in 1951 through the merger of two institutions of higher education in Shanghai, and has since become one of the most prestigious universities in China. ECNU is known for its strong research and academic programs, and has @ reputation for producing top-quality graduates in a wide range of fields. The university has a diverse student body, with students from all over CChina and around the world. ECNU is also known for its strong ties to industry and business, and has a number of research centers and institutes that focus on areas such as artificial intelligence, biotechnology, and environmental science. In addition % Examples Topic 3 to its academic programs, ECNU is also known for its beautiful campus, which features a mix of traditional Chinese architecture â and modern facilities. Overall, ECNU is a highly respected and well-regarded institution of higher education, and is a great choice for students who are locking for a challenging and rewarding academic experience. | 2308.02773#9 | 2308.02773#11 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#11 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | Y Open aA Reference: Emotional Support â + East China Normal University ~ Wikipedia â + East China Normal University + Introduction to ECNU-East China Normal University Essay Assessment Socratic Teaching Course Guidance Career Planning © Regenerate response i XX Open aa Type Retrieval s 0} @ > Figure 3: Demo of EduChat. stage, we develop EduChatâ s pedagogical skills by fine-tuning the model on our carefully curated data, including retrieval-augmented open QA, emotional support, Socratic teaching and essay assessment datasets mentioned in Section 4.2. # 5.2 Online Knowledge Retrieval | 2308.02773#10 | 2308.02773#12 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#12 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | "Calculator: Disable" signifies the modelâ s inability to utilize a calculator; 3) Skill Selection: Teachers in various settings possess unique communication skills, such as Socratic Teaching or Psychology- based Emotional Support. To cater to specific sce- narios, we include function names at the end of the system prompt, which activates corresponding abilities based on the sceneâ s requirements. Existing generative LLMs all suffer from the issues of generating hallucinations and outdated informa- tion, which is detrimental to an educational model. To mitigate this problem, we introduce self-check as shown in Figure 2. Specifically, when online knowledge retrieval is enabled, the model picks useful retrieval results by asking itself "Is this help- ful for answering the question?" and append filtered snippets before the dialogue history. # 5.3 System Prompt Design | 2308.02773#11 | 2308.02773#13 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#13 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | Teachers always utilize various tools with different skills to enhance their teaching across different sub- jects. To enable EduChat to emulate an authentic teacher-student interaction, we carefully craft the system prompt that consists of personal profile, tool usage and skill selection (see Figure 2). Detailed settings can be found in Table 2. # 5.4 Demonstration We also develop a user-friendly demo system for EduChat (see Figure 3). Upon logging in, users can select from various functions, such as Open QA and Emotional Support, each offering a scene-specific system prompt to activate the corresponding ability. With this intuitive interface, users can easily engage in interactive conversations with EduChat to assist students, teachers and parents. Additionally, the system is designed to be adaptive, continuously learning from user interactions to further improve its capabilities and provide more personalized and effective assistance over time. | 2308.02773#12 | 2308.02773#14 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#14 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | # 6 Experimental Results 1) Personal Profile: To remind the model of its own identity, the system prompt begins with: "EduChat is a conversational language model de- veloped by East China Normal University."; 2) Tool Usage: To regulate tool availability, the second part of the system prompt commences with "EduChatâ s tools:", listing all tool names and their respective accessibility. For instance, "Web search: Enable" indicates the modelâ s ability to use retrieval, while # 6.1 Resutls of C-Eval Table 1 presents the results of our model on the C- Eval benchmark (Huang et al., 2023), a comprehen- sive Chinese evaluation suite for foundation mod- els. The dataset consists of 13,948 multi-choice questions, spanning 52 diverse disciplines and cat- egorized into four difficulty levels. Analyzing the table, we observe that our model achieves com- mendable performance compared to models with | 2308.02773#13 | 2308.02773#15 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#15 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | # Chinese # Translate to English # Retrieval-Augmented Open QA User: ee ae tif? 2 User: Who is the author of the View the Sea? EduChat: (UIE) MITE Bh. GPR AL SLE TONER, Hides â i iE : Be ai fait ADH HORACE GEENA. PTR BE ae oe PPMP HAM HE, AE PRI AR EEL # Br RE: Wit ite ERE EduChat: | 2308.02773#14 | 2308.02773#16 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#16 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | The author of the View the Sea was Cao Cao, a poet in the late Eastern Han Dynasty. This poem is written by Cao Cao when he climbed the mountain and looked at the sea in Jieshi Mountain. It depicts the magnificence of the rivers and mountains of the motherland. It not only depicts the magnificence of the mountains and the sea, but also expre: the poet's enterprising spirit with the scenery and the world in mind. This poem is regarded as a classic of ancient Chinese poetry and one of Cao Cao's representative works. | 2308.02773#15 | 2308.02773#17 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#17 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | # Reference: # View_the_sea_ Baidu_Baike Socratic Teaching 3? uo itm ALY ZS ADK SSM? SS AE AL aE FAT NI 2 User: FR 4s itt EduChat: JZ A: Fil Ri ip RU 2 AK BCA NS BLN 2 J, ARAVA Y iit FL AOA SH I « SHAT FEAL A AE « NIG ASE AE A RW FATA AEG 2 Leu, 1, 3, 5, 7, 98 User it fut EduChat: Bel) A] WA Fil ES 2 AA BS RHF HAAS: Sn= (1/2)*n (al+an), Jal ES IER BONEN Sil. User: HEIR A RIE ANTUE HEA MBEAN EB EduChat: 1bZ,, ri al + (N-I)* de CPA AE SL SSNS an, ABA SENT ZS aI rE ERE PILZ i BON, BEI ea at FY LATER AEB Fe? ATTA. Tel, SE 2e BONN T N-1)*d, BEAM LAG Ban =3+ (6-1)*2, Ban=13. y 7,9, 11, 13. REN, ROW? PAE, 3&6 User: Betti EduChat: 57/4, T, WK. WR Ae a, BALIN AY DA fa aR. User: | 2308.02773#16 | 2308.02773#18 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#18 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | How do you find the first n terms of an arithmetic sequence? EduChat: Are you asking for the formula for the sum of the first n terms of an arithmetic sequence, or how to apply the formula to find the sum of the first n terms? User: I don't know the formula for the sum of the first n terms of an arithmetic sequence. EduChat: Well, do you know what an arithmetic sequence is? User: Not really. EduChat: Okay, let's first understand what an arithmetic sequence is. An arithmetic sequence is a sequence in which the difference between any term and the one before it is constant. For example, 1, 3, 5, 7, 9 is an arithmetic sequence because the difference between each term and the one before it User: So how do you find the sum of the first N terms? | 2308.02773#17 | 2308.02773#19 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#19 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | EduChat: We can use the formula for the sum of an arithmetic sequence to solve it. The formula for the sum of the first N terms of an arithmetic sequence is: Sn = 1/2 * n* (al + an), where al is the first term of the arithmetic sequence, and an is the Nth term. User: But I don't know what the Nth term is. EduChat: Well, we can derive the Nth term from known conditions. If we know the first term of an arithmetic sequence al, the common difference d, and the Nth term an, then the formula for the Nth term is User: What do you mean by common difference? | 2308.02773#18 | 2308.02773#20 | 2308.02773 | [
"2302.13971"
]
|
2308.02773#20 | EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education | EduChat: The common difference refers to the difference between any two terms in an arithmetic sequence. In an arithmetic sequence, the difference between each term and the one before it is the same, and this equal difference is the common difference. User: Can you give me an example? EduChat: Of course. For example, if the first term the common difference is 2, what is the 6th term? A 3+ (6-1) * 2, which give: quence are 3, 5, 7,9, 11, 13. stand now, thank you. | 2308.02773#19 | 2308.02773#21 | 2308.02773 | [
"2302.13971"
]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.