Implementing vanilla autoencoders

An autoencoder comprises of the following two networks:

  • Encoder: An encoder encodes its input, , into a hidden representation, . The output of an encoder unit is as follows:

h = g(Wxi+b)

where, xi Rn, W  Rd x n, Rd.

  • Decoder: A decoder reconstructs the input from the hidden representation, h. The output of a decoder unit is as follows:

where, W* ∈ Rn x d, h ∈ Rd, c ∈ Rn.

An autoencoder neural network ...

Get Deep Learning with R Cookbook now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.