Sparse-Autoencoders

Sparse-Autoencoders copied to clipboard

Sparse Autoencoders

Sparsity constraint is imposed here by using a KL-Divergence penalty. See this for a detailed explanation of sparse autoencoders.

The FashionMNIST dataset was used for this implementation. Figures shown below are obtained after 1 epoch:

Using sparsity penalty:

Normal autoencoder