pages/2_DIFFERENCES_BETWEEN_ML&DL.py

import streamlit as st

st.markdown(
    """
    <style>
    .stApp {
        background-image: url("https://huggingface.co/spaces/ronakreddy18/Zerotoheroinmachinelearning/resolve/main/ai-technology-brain-background-digital-transformation-concept.jpg");
        background-size: cover;
        background-repeat: no-repeat;
        background-attachment: fixed;
    }
    </style>
    """,
    unsafe_allow_html=True
)

# Header Section
st.markdown("<h1>DIFFERENCES BETWEEN ML AND DL</h1>", unsafe_allow_html=True)

# Content for Machine Learning
st.markdown(
    """
    <div class="division">
        <h2>Key Points in Machine Learning</h2>
        <ul>
            <li><strong>Data Points:</strong> Machine Learning models can be trained on smaller datasets.</li>
            <li><strong>Hardware for Training:</strong> Training can be done on standard CPUs.</li>
            <li><strong>Training Time:</strong> Requires less time due to smaller dataset sizes and simpler algorithms.</li>
            <li><strong>Algorithm Complexity:</strong> Includes simpler models like linear regression and more complex ones like decision trees or random forests.</li>
            <li><strong>Analysis Complexity:</strong> Involves identifying patterns and relationships in data.</li>
            <li><strong>Application Areas:</strong> Widely used for tasks such as regression, classification, and clustering.</li>
        </ul>
    </div>
    """,
    unsafe_allow_html=True
)
# Content for Deep Learning
st.markdown(
    """
    <div class="division">
        <h2>Key Points in Deep Leraning</h2>
        <ul>
            <li><strong>Data Points:</strong> Machine Learning models csan be trained on larger dataset.</li>
            <li><strong>Hardware for Training:</strong> Training can be done on GPUs.</li>
            <li><strong>Training Time:</strong> Requires more time due to larger dataset sizes and bigger algorithms.</li>
            <li><strong>Algorithm Complexity:</strong> Deep learning algorithms are based on artificial neural networks that consist of multiple layers and nodes..</li>
            <li><strong>Analysis Complexity:</strong>Uses complex neural networks with multiple layers to analyze more intricate patterns and relationships.</li>
            <li><strong>Application Areas:</strong> Deep learning is mostly used for complex tasks such as image and speech recognition, natural language processing, and autonomous systems.</li>
        </ul>
    </div>
    """,
    unsafe_allow_html=True
)