ML Katas

Build and train a Siamese network on a dataset like MNIST. The network takes pairs of images as input and learns to determine if they belong to the same class (a positive pair) or different classes (a negative pair). The loss function can be a contrastive loss or a triplet loss. The goal is to learn an embedding space where similar images are close together and dissimilar images are far apart.

Verification: After training, embed a small test set and visualize the embeddings using a dimensionality reduction technique like PCA or t-SNE. You should see distinct clusters for different digits, indicating that the network has learned a meaningful representation.