...

/

Autoencoders as Neural Network Version of PCA

Autoencoders as Neural Network Version of PCA

Exploring autoencoders as a neural network version of PCA for dimension reduction and feature representation.

Background

An autoencoder is a reconstruction model. It attempts to reconstruct its inputs from itself as depicted below:

xf(x)zencodingg(z)x^decoding.x → \underbrace{f(x) → z}_{\text{encoding}} → \underbrace{g(z) → \hat{x}}_{\text{decoding}}.

An autoencoder is made of two modules: encoder and decoder.

As their names indicate, an encoder ff encodes input ...