Autoencoder

An autoencoder, autoassociator or Diabolo network is an artificial neural network used for unsupervised learning of efficient codings. The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for the purpose of dimensionality reduction. Recently, the autoencoder concept has become more widely used for learning generative models of data.

Auto-Associative Neural Network (AutoEncoder).

Auto-Encoder

Stacked Auto-Encoder

Sparse Auto-Encoder

Denoising Auto-Encoder (dA)

Stacked Denoising Auto-Encoder (SdA)

See also

• Deep Learning
• Masked Autoencoders Are Scalable Vision Learners (facebook)

Favorite site

• Wikipedia (en) Autoencoder
• 1. Introduction Auto-Encoder
• 1. 오토인코더(Sparse Autoencoder) 1 – AutoEncoders & Sparsity
• UFLDL Tutorial
  • Ufldl - Autoencoders and Sparsity