Correlation of internal representations in feed-forward neural networks

DOI10.1088/0305-4470/29/13/003MaRDI QIDQ4390041zbMATH OpenOpenAlexFDO

Authors Andreas Engel

Publication date 20 August 1998

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/9604070

zbMATH Keywords

feed-forward multilayer neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: Feed-forward multilayer neural networks implementing random input-output mappings develop characteristic correlations between the activity of their hidden nodes which are important for the understanding of the storage and generalization performance of the network. It is shown how these correlations can be calculated from the joint probability distribution of the aligning fields at the hidden units for arbitrary decoder function between hidden layer and output. Explicit results are given for the parity-, and-, and committee-machines with arbitrary number of hidden nodes near saturation.

Recommendations

• Properties of neural networks storing spatially correlated patterns
• The effect of correlations in neural networks
• Storage of sets of correlated data in neural network memories
• Function evaluation with feedforward neural networks

Cited in

(3)

• Techniques of replica symmetry breaking and the storage problem of the McCulloch-Pitts neuron
• Correlations of random classifiers on large data sets
• The effect of correlations in neural networks

This page was built for publication: Correlation of internal representations in feed-forward neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4390041)