Bifurcation analysis in an associative memory model
Disordered Systems and Neural Networks
2007-05-23 v3
Abstract
We previously reported the chaos induced by the frustration of interaction in a non-monotonic sequential associative memory model, and showed the chaotic behaviors at absolute zero. We have now analyzed bifurcation in a stochastic system, namely a finite-temperature model of the non-monotonic sequential associative memory model. We derived order-parameter equations from the stochastic microscopic equations. Two-parameter bifurcation diagrams obtained from those equations show the coexistence of attractors, which do not appear at absolute zero, and the disappearance of chaos due to the temperature effect.
Cite
@article{arxiv.cond-mat/0309651,
title = {Bifurcation analysis in an associative memory model},
author = {Masaki Kawamura and Ryuji Tokunaga and Masato Okada},
journal= {arXiv preprint arXiv:cond-mat/0309651},
year = {2007}
}
Comments
19 pages