Deep learning via semi-supervised embedding

Abstract

We show how nonlinear embedding algorithms popular for use with <i>shallow</i> 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 <i>deep</i> learning whilst yielding competitive error rates compared to those methods, and existing <i>shallow</i> semi-supervised techniques.

DOI: 10.1145/1390156.1390303

Extracted Key Phrases

Showing 1-10 of 236 extracted citations
0501002008200920102011201220132014201520162017
Citations per Year

399 Citations

Semantic Scholar estimates that this publication has received between 322 and 497 citations based on the available data.

See our FAQ for additional information.