logo Idiap Research Institute        
 [BibTeX] [Marc21]
Deep Learning via Semi-Supervised Embedding
Type of publication: Book chapter
Citation: Weston_SPRINGER_2012
Booktitle: In Neural Networks: Tricks of the Trade
Edition: Second
Year: 2012
Publisher: Springer
Abstract: 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.
Keywords: deep learning, embedding, semi-supervised learning
Projects Idiap
Authors Weston, Jason
Ratle, Frédéric
Mobahi, Hossein
Collobert, Ronan
Editors Montavon, Grégoire
Orr, Geneviève
Müller, K. -R.
Added by: [UNK]
Total mark: 0
  • Weston_SPRINGER_2012.pdf