Autoencoders
arXiv:2003.05991v259 citations
AI Analysis
This is an incremental survey paper for researchers and practitioners in machine learning.
The paper surveys different types of autoencoders, which are neural networks designed to encode inputs into compressed representations and decode them to reconstruct the original input, describing their applications and use-cases.
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.