Content deleted Content added
→Purpose: fixed misuse of the term "autoencoder"; this refers to the whole network consisting of encoder and decoder (hence "auto" encoder), not its individual layers. |
No edit summary |
||
Line 1:
{{machine learning bar}}
[[File:Autoencoder_structure.png|350x350px|Schematic structure of an autoencoder with 3 fully connected hidden layers.|thumb]]
An '''autoencoder''' is a type of [[artificial neural network]] used to learn [[Feature learning|efficient data codings]] in an [[unsupervised learning|unsupervised]] manner.<ref>{{cite journal|doi=10.1016/j.neucom.2008.04.030|title=Modeling word perception using the Elman network|journal=Neurocomputing|volume=71|issue=16–18|pages=3150|year=2008|last1=Liou|first1=Cheng-Yuan|last2=Huang|first2=Jau-Chi|last3=Yang|first3=Wen-Chie}}</ref><ref>{{cite journal|doi=10.1016/j.neucom.2013.09.055|title=Autoencoder for words|journal=Neurocomputing|volume=139|pages=84|year=2014|last1=Liou|first1=Cheng-Yuan|last2=Cheng|first2=Wei-Chen|last3=Liou|first3=Jiun-Wei|last4=Liou|first4=Daw-Ran}}</ref> The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for [[dimensionality reduction]]. Along with the reduction side, a reconstructing side is learnt, where the autoencoder tries to generate from the reduced encoding a representation as close as possible to its original input, hence its name. Recently, the autoencoder concept has become more widely used for learning [[generative model]]s of data.<ref name="VAE">{{cite arxiv|eprint=1312.6114|author1=Diederik P Kingma|title=Auto-Encoding Variational Bayes|last2=Welling|first2=Max|class=stat.ML|year=2013}}</ref><ref name="gan_faces">Generating Faces with Torch, Boesen A., Larsen L. and Sonderby S.K., 2015 {{url|http://torch.ch/blog/2015/11/13/gan.html}}</ref> Some of the most powerful AI in the 2010s have involved sparse autoencoders stacked inside of deep neural networks.<ref name=domingos>{{cite book |first1=Pedro |last1=Domingos |author-link=Pedro Domingos|year=2015|title=[[The Master Algorithm|The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World]] |publisher= Basic Books |isbn= 978-046506192-1 |chapter=4 |at= "Deeper into the Brain" subsection}}</ref>
==Purpose==
| |||