Title of article
Z(2) gauge neural network and its phase structure
Author/Authors
Takafuji، نويسنده , , Yusuke and Nakano، نويسنده , , Yuki and Matsui، نويسنده , , Tetsuo، نويسنده ,
Issue Information
روزنامه با شماره پیاپی سال 2012
Pages
20
From page
5285
To page
5304
Abstract
We study general phase structures of neural-network models that have Z(2) local gauge symmetry. The Z(2) spin variable S i = ± 1 on the i -th site describes a neuron state as in the Hopfield model, and the Z(2) gauge variable J i j = ± 1 describes a state of the synaptic connection between j -th and i -th neurons. The gauge symmetry allows for a self-coupling energy among J i j ’s such as J i j J j k J k i , which describes reverberation of signals. Explicitly, we consider the three models; (I) an annealed model with full and partial connections of J i j , (II) a quenched model with full connections where J i j is treated as a slow quenched variable, and (III) a quenched three-dimensional lattice model with the nearest-neighbor connections. By numerical simulations, we examine their phase structures paying attention to the effect of the reverberation term, and compare them with each other and with the annealed 3D lattice model which has been studied beforehand. By noting the dependence of thermodynamic quantities upon the total number of sites and the connectivity among sites, we obtain a coherent interpretation to understand these results. Among other things, we find that the Higgs phase of the annealed model is separated into two stable spin-glass phases in the quenched models (II) and (III).
Keywords
neural network , lattice gauge theory , Phase structure
Journal title
Physica A Statistical Mechanics and its Applications
Serial Year
2012
Journal title
Physica A Statistical Mechanics and its Applications
Record number
1735996
Link To Document