2011/9/28 鄭昌源教授專題演講
演講者:
單 位:
日 期:2011年9月28日 PM 14:30
地 點:國立高雄大學理學院408室
講 題:Multistability and Chaos in Artificial Neural System
摘 要:
A delayed neural network with a valid nonmonotonic activation function is explored. Coexistence of multiple stable equilibria and chaotic dynamics are demonstrated in this discrete dynamical system. Specifically, $2^m$ stable stationary solutions and their basins of attraction are found for a loop with $m$-neurons network. The theory is established by formulating parameter conditions according to a geometric observation. The networks are further confirmed exhibit chaotic dynamics when the magnitudes of inhibitory self-feedback weights are large enough. The scenario is based on building a snap-back repeller and Marotto's theorem.
