This paper presents a novel asymptotical stability analysis of the equilibrium points in the unit hypercube for the Brain-State-in-a-Box neural model. Some sufficient conditions for the asymptotical stability of equilibrium points are derived using Ostrowskis theorem and the similarity transformation approach. Simulation examples are given to illustrate the effectiveness of new analysis method.
Anderson J A, Silverstein J W, Ritz S A, et al. Distinctive features, categorical perception and probability learning: Some applications of a neural model, in Neurocomputing: Foundations of Research,Anderson J A and Rosenfeld E. Eds. Cambridge, MA: MIT Press, 1988, Ch.2-Ch.4.[2]Golden R M .The Brain-State-in-a-Box neural model is a gradient descent algorithm[J].Journal of Mathematical Psychology.1986, 30(1):73-80[3]Greenberg H J. Equilibria of the Brain-State-in-a-Box (BSB) neural mode. IEEE Trans.on Neural Networks, 1988, 1(4): 323-324.[4]Trans. on Neural Networks, 1992, 3(1): 86-94.[5]Lillo W E, Miller D C, Hui S, Zak S H. Synthesis of Brain-State-in-a-Box (BSB) based associative memories, IEEE Trans[J].on Neural Networks.1994, 5(5):730-734[6]黄琳.系统与控制理论中的线性代数.北京:科学出版社,1986,第5章.[7]张锦炎.常微分方程几何理论与分支问题.北京:北京大学出版社,1981,第9章.