Update README.md

README.md

@@ -6,10 +6,9 @@ tags:
 
 ## Model description
 
-Metric learning aims to measure the similarity among data samples and to learn embedding models. In the context of metric learning to learn embedding models, the motivation is to embed inputs in an embedding space such that similar images 
-are close together in that space while dissimilar ones are far away.  
+Metric learning aims to measure the similarity among data samples and to learn embedding models. The motivation is to embed inputs in an embedding space such that similar images are close together in that space while dissimilar ones are far away.  
 
-These models once trained can produce embeddings for downstream systems where such similarity is useful.  
+The model in this repo is an example which demonstrates the capabilities of metric learning to create embeddings. These embeddings are then used to perform Image Similarity Search. 
 
 Full credits to [Mat Kelcey](https://twitter.com/mat_kelcey) for this work.