Gauged Neural Network: Phase Structure, Learning, and Associative Memory
Abstract
A gauge model of neural network is introduced, which resembles the Z(2) Higgs lattice gauge theory of high-energy physics. It contains a neuron variable on each site of a 3D lattice and a synaptic-connection variable on each link . The model is regarded as a generalization of the Hopfield model of associative memory to a model of learning by converting the synaptic weight between and to a dynamical Z(2) gauge variable . The local Z(2) gauge symmetry is inherited from the Hopfield model and assures us the locality of time evolutions of and and a generalized Hebbian learning rule. At finite "temperatures", numerical simulations show that the model exhibits the Higgs, confinement, and Coulomb phases. We simulate dynamical processes of learning a pattern of and recalling it, and classify the parameter space according to the performance. At some parameter regions, stable column-layer structures in signal propagations are spontaneously generated. Mutual interactions between and induce partial memory loss as expected.
Cite
@article{arxiv.cond-mat/0203136,
title = {Gauged Neural Network: Phase Structure, Learning, and Associative Memory},
author = {Motohiro Kemuriyama and Tetsuo Matsui and Kazuhiko Sakakibara},
journal= {arXiv preprint arXiv:cond-mat/0203136},
year = {2009}
}
Comments
17 pages, 18 figures. Final Version