Deep learning via semi-supervised embedding

作者：J. Weston, F. Ratle, H. Mobahi, R. Collobert · 发表于：International Conference on Machine Learning · 年份：2008 · DOI：10.1145/1390156.1390303 · 被引用次数：1071 · 研究领域：Computer Science

We show how nonlinear embedding algorithms popular for use with shallow semi-supervised 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.