Golden
Autoencoder

Autoencoder

An autoencoder neural network is an algorithm that is unsupervised and which applies back-propagation

All edits

Edits on 16 Aug 2019
Jude Gomila
Jude Gomila approved a suggestion from Golden's AI on 16 Aug 2019 5:45 pm
Edits made to:
Article (+24/-24 characters)

Article

There are several types of autoencoders such as denoising autoencoders, sparse autoencoders, variational autoencodersvariational autoencoders (VAE), and contractive autoencoders (CAE).

Edits on 15 Aug 2019
Daniel Frumkin"Added article and description"
Daniel Frumkin edited on 15 Aug 2019 1:55 pm
Edits made to:
Description (+101 characters)
Article (+913 characters)
Categories (+2 topics)
Topic thumbnail

Autoencoder

An autoencoder neural network is an algorithm that is unsupervised and which applies back-propagation

Article

An autoencoder is a neural network that uses an algorithm to learn through back-propagation, in an unsupervised manner. The autoencoder tries to learn an approximate to an identity function by placing constraints on the network to gather information about the structure of the data of the function.



Another way to describe an autoencoder is as an Unsupervised Pertained Network, or UPN. Each autoencoder is composed of three layers: an input layer, an hidden (encoding) layer, and a decoding layer. This makes them similar to principle components analysis, or PCA as some of their traits include an unsupervised ML algorithm, they minimize the same objective function as a PCA, and are a neural network with a target output that is the same as its input.

...

There are several types of autoencoders such as denoising autoencoders, sparse autoencoders, variational autoencoders (VAE), and contractive autoencoders (CAE).

Categories

Edits on 1 Jan 2017
Golden AI"Initial topic creation"
Golden AI created this topic on 1 Jan 2017 12:00 am
Edits made to:
Article
Topic thumbnail

 Autoencoder

An autoencoder neural network is an algorithm that is unsupervised and which applies back-propagation

No more activity to show.