Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
9727569 | Physica A: Statistical Mechanics and its Applications | 2005 | 29 Pages |
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 Sx=±1 on each site x of a 3D lattice and a synaptic-connection variable Jxμ=±1 on each link (x,x+μ^)(μ=1,2,3). 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 x and x+μ^ to a dynamical Z(2) gauge variable Jxμ. The local Z(2) gauge symmetry is inherited from the Hopfield model and assures us the locality of time evolutions of Sx and Jxμ 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 Sx 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 Sx and Jxμ induce partial memory loss as expected.
Related Topics
Physical Sciences and Engineering
Mathematics
Mathematical Physics
Authors
Motohiro Kemuriyama, Tetsuo Matsui, Kazuhiko Sakakibara,