首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Z(2) gauge neural network and its phase structure
Authors:Yusuke Takafuji  Yuki NakanoTetsuo Matsui
Institution:Department of Physics, Kinki University, Higashi-Osaka, 577-8502, Japan
Abstract:We study general phase structures of neural-network models that have Z(2) local gauge symmetry. The Z(2) spin variable Si=±1Si=±1 on the ii-th site describes a neuron state as in the Hopfield model, and the Z(2) gauge variable Jij=±1Jij=±1 describes a state of the synaptic connection between jj-th and ii-th neurons. The gauge symmetry allows for a self-coupling energy among JijJij’s such as JijJjkJkiJijJjkJki, which describes reverberation of signals. Explicitly, we consider the three models; (I) an annealed model with full and partial connections of JijJij, (II) a quenched model with full connections where JijJij 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
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号