Sciweavers

ICML
2008
IEEE

Deep learning via semi-supervised embedding

14 years 11 months ago
Deep learning via semi-supervised embedding
We show how nonlinear embedding algorithms popular for use with shallow semisupervised 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.
Frédéric Ratle, Jason Weston, Ronan
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2008
Where ICML
Authors Frédéric Ratle, Jason Weston, Ronan Collobert
Comments (0)