PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Layer-wise Analysis of Deep Networks with Gaussian Kernels
Gregoire Montavon, Mikio Braun and Klaus-Robert Müller
Advances in Neural Information Processing Systems (NIPS) Volume 23, pp. 1678-1686, 2010.

Abstract

Deep networks can potentially express a learning problem more efficiently than local learning machines. While deep networks outperform local learning machines on some problems, it is still unclear how their nice representation emerges from their complex structure. We present an analysis based on Gaussian kernels that measures how the representation of the learning problem evolves layer after layer as the deep network builds higher-level abstract representations of the input. We use this analysis to show empirically that deep networks build progressively better representations of the learning problem and that the best representations are obtained when the deep network discriminates only in the last layers.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Theory & Algorithms
ID Code:7999
Deposited By:Mikio braun
Deposited On:17 March 2011