Covariance Phasor Neural Network as a Mean field model

  • Takahashi, Haruhisa (Department of Information and Communication Engineering, The University of Electro-Communication)
  • Published : 2002.07.01

Abstract

We present a phase covariance model that can well represent stimulus intensity as well af feature binding (i.e., covariance). The model is represented by complex neural equations, which is a mean field model of stochastic neural model such as Boltzman machine and sigmoid belief networks.

Keywords