CHAPTER Weston_SPRINGER_2012/IDIAP Deep Learning via Semi-Supervised Embedding Weston, Jason Ratle, Frédéric Mobahi, Hossein Collobert, Ronan Montavon, Grégoire Ed. Orr, Geneviève Ed. Müller, K. -R. Ed. deep learning embedding semi-supervised learning EXTERNAL https://publications.idiap.ch/attachments/papers/2012/Weston_SPRINGER_2012.pdf PUBLIC In Neural Networks: Tricks of the Trade 2012 Springer 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.