Autoencoder: Difference between revisions

Revision as of 14:19, 16 August 2024

Revision as of 14:21, 16 August 2024

Line 185:

=== Machine translation ===

Autoencoders have been applied to [[machine translation]], which is usually referred to as [[neural machine translation]] (NMT).<ref>{{cite arXiv |eprint=1409.1259|last1=Cho|first1=Kyunghyun|author2=Bart van Merrienboer|last3=Bahdanau|first3=Dzmitry|last4=Bengio|first4=Yoshua|title=On the Properties of Neural Machine Translation: Encoder-Decoder Approaches|class=cs.CL|date=2014}}</ref><ref>{{cite arXiv |eprint=1409.3215|last1=Sutskever|first1=Ilya|last2=Vinyals|first2=Oriol|last3=Le|first3=Quoc V.|title=Sequence to Sequence Learning with Neural Networks|class=cs.CL|date=2014}}</ref> Unlike traditional autoencoders, the output does not match the input - it is in another language. In NMT, texts are treated as sequences to be encoded into the learning procedure, while on the decoder side sequences in the target language(s) are generated. [[Language]]-specific autoencoders incorporate further [[linguistic]] features into the learning procedure, such as Chinese decomposition features.<ref>{{cite arXiv |eprint=1805.01565|last1=Han|first1=Lifeng|last2=Kuang|first2=Shaohui|title=Incorporating Chinese Radicals into Neural Machine Translation: Deeper Than Character Level|class=cs.CL|date=2018}}</ref> Machine translation is rarely still done with autoencoders, due to the availability of more effective [[Transformer (machine learning model)|transformer]] networks.

=== Image generation ===

Due to the specifics of an autoencoder's structure, it can be used to reduce the dimensionality of an input image. These new values would be stored in the latent vector of the neural network. By recombining the layers of this pretrained model, starting with the latent vector, a new model could be created. The inputs in this case are the compressed values, whereas the initial images will serve as outputs to the neural network. Modifying the inputs will directly generate new images.

==See also==

o the neutral network. By modifying thef

* [[Representation learning]]

* [[Sparse dictionary learning]]