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.
Loading...
Name
Weston_SPRINGER_2012.pdf
Access type
openaccess
Size
873.55 KB
Format
Adobe PDF
Checksum (MD5)
2b36b060e2c00673184b28825b90a8d2