Analytical and Numerical Study of Internal Representations in Multilayer Neural Networks with Binary Weights

arxiv: cond-mat/9604102 · v1 · submitted 1996-04-16 · ❄️ cond-mat

Analytical and Numerical Study of Internal Representations in Multilayer Neural Networks with Binary Weights

Simona Cocco , Remi Monasson , Riccardo Zecchina This is my paper

classification ❄️ cond-mat

keywords binaryinternallearningnumericalrepresentationsweightsagreementanalytical

0 comments p. Extension

read the original abstract

We study the weight space structure of the parity machine with binary weights by deriving the distribution of volumes associated to the internal representations of the learning examples. The learning behaviour and the symmetry breaking transition are analyzed and the results are found to be in very good agreement with extended numerical simulations.

This paper has not been read by Pith yet.

Analytical and Numerical Study of Internal Representations in Multilayer Neural Networks with Binary Weights

discussion (0)