A Manifold Learning Perspective on Representation Learning: Learning Decoder and Representations without an Encoder

A Manifold Learning Perspective on Representation Learning: Learning Decoder and Representations without an Encoder

Autoencoders are commonly used in representation learning. They consist of an encoder and a decoder, which provide a straightforward method to map <i>n</i>-dimensional data in input space to a lower <i>m</i>-dimensional representation space and back. The decoder itself define...

Full description

Bibliographic Details
Main Authors: Viktoria Schuster, Anders Krogh
Format: Article
Language:English
Published: MDPI AG 2021-10-01
Series:Entropy
Subjects:
representation learning
manifold learning
neural networks
autoencoders
Online Access:https://www.mdpi.com/1099-4300/23/11/1403

Internet

https://www.mdpi.com/1099-4300/23/11/1403

Similar Items