Taking Apart Autoencoders: How do They Encode Geometric Shapes ?

ICLR 2018 Alasdair NewsonAndres AlmansaYann GousseauSaid Ladjal

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... (read more)

PDF Abstract


No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper