The reviewed record of science sign in
Pith

arxiv: 2006.11569 · v1 · pith:NYXOHC7T · submitted 2020-06-20 · cs.LG · cond-mat.dis-nn· cond-mat.stat-mech· q-bio.NC· stat.ML

Weakly-correlated synapses promote dimension reduction in deep neural networks

Reviewed by Pithpith:NYXOHC7Topen to challenge →

classification cs.LG cond-mat.dis-nncond-mat.stat-mechq-bio.NCstat.ML
keywords correlationssynapsesdimensionreductiondeepneuralsynapticaffect
0
0 comments X
read the original abstract

By controlling synaptic and neural correlations, deep learning has achieved empirical successes in improving classification performances. How synaptic correlations affect neural correlations to produce disentangled hidden representations remains elusive. Here we propose a simplified model of dimension reduction, taking into account pairwise correlations among synapses, to reveal the mechanism underlying how the synaptic correlations affect dimension reduction. Our theory determines the synaptic-correlation scaling form requiring only mathematical self-consistency, for both binary and continuous synapses. The theory also predicts that weakly-correlated synapses encourage dimension reduction compared to their orthogonal counterparts. In addition, these synapses slow down the decorrelation process along the network depth. These two computational roles are explained by the proposed mean-field equation. The theoretical predictions are in excellent agreement with numerical simulations, and the key features are also captured by a deep learning with Hebbian rules.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.