Deep Learning via Semi-Supervised Embedding

We show how nonlinear embedding algorithms popular for use with "shallow" semi-supervised learning techniques such as kernel methods can be easily applied to deep multi-layer architectures, either as a regularizer at the output layer, or on each layer of the architecture. This trick 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.


Editor(s):
Montavon, Grégoire
Orr, Geneviève
Müller, K. -R.
Published in:
Neural Networks: Tricks of the Trade, 639-655
Year:
2012
Publisher:
Springer
ISBN:
978-3-642-35288-1
Keywords:
Laboratories:




 Record created 2013-12-19, last modified 2018-08-11

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)