Deep learning via semi-supervised embedding
Details
Serval ID
serval:BIB_C1D175E7D9BE
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Institution
Title
Deep learning via semi-supervised embedding
Title of the conference
Proceedings of the 25th international conference on Machine learning
Publisher
ACM 2008 Article
ISBN
978-1-60558-205-4
Publication state
Published
Issued date
2008
Pages
1168-1175
Language
english
Notes
Weston2008
Abstract
We show how nonlinear embedding algorithms popular for use with shallow
semi-supervised learning techniques such as kernel methods can be
applied to deep multilayer architectures, either as a regularizer
at the output layer, or on each layer of the architecture. This provides
a simple alternative to existing approaches to deep learning whilst
yielding competitive error rates compared to those methods, and existing
shallow semi-supervised techniques.
semi-supervised learning techniques such as kernel methods can be
applied to deep multilayer architectures, either as a regularizer
at the output layer, or on each layer of the architecture. This provides
a simple alternative to existing approaches to deep learning whilst
yielding competitive error rates compared to those methods, and existing
shallow semi-supervised techniques.
Create date
25/11/2013 18:18
Last modification date
20/08/2019 16:36
Usage data
