Autoencoders that don't overfit towards the Identity

NeurIPS 2020

Autoencoders that don't overfit towards the Identity

Dec 06, 2020
|
31 views
|
Details
An autoencoder is a specific type of a neural network, which is mainly designed to encode the input into a compressed and meaningful representation, and then decode it back such that the reconstructed input is similar as possible to the original one. This chapter surveys the different types of autoencoders that are mainly used today. It also describes various applications and use-cases of autoencoders. Speakers: Harald Steck

Comments
loading...