Taking Apart Autoencoders: How do They Encode Geometric Shapes ?

Alasdair Newson, Andres Almansa, Yann Gousseau, Said Ladjal

Feb 15, 2018 (modified: Feb 15, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: We study the precise mechanisms which allow autoencoders to encode and decode a simple geometric shape, the disk. In this carefully controlled setting, we are able to describe the specific form of the optimal solution to the minimisation problem of the training step. We show that the autoencoder indeed approximates this solution during training. Secondly, we identify a clear failure in the generalisation capacity of the autoencoder, namely its inability to interpolate data. Finally, we explore several regularisation schemes to resolve the generalisation problem. Given the great attention that has been recently given to the generative capacity of neural networks, we believe that studying in depth simple geometric cases sheds some light on the generation process and can provide a minimal requirement experimental setup for more complex architectures.
  • TL;DR: We study the functioning of autoencoders in a simple setting and advise new strategies for their regularisation in order to obtain bettre generalisation with latent interpolation in mind for image sythesis.
  • Keywords: autoencoders, CNN, image synthesis, latent space