STABILITY AND OPTIMIZATION ANALYSES OF THE GENERALIZED BRAIN-STATE-IN-A-BOX NEURAL-NETWORK MODEL

被引:24
作者
GOLDEN, RM
机构
[1] University of Texas, Dallas
关键词
D O I
10.1006/jmps.1993.1017
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Anderson's brain-state-in-a-box (BSB) neural network model may be viewed as a version of Hopfield's two-state neural model with continuous rather than discrete states and synchronous updating. A generalization of the BSB model which allows each model neuron in the system to have a bias and its own maximum and minimum firing rate is considered. Moreover, the generalization does not require that the matrix of connection weights be symmetric. A method of choosing the step constant of the algorithm is then described which guarantees that the generalized discrete-time BSB model: (i) approaches the largest set of system equilibrium points, and (ii) minimizes the Boltzmann machine quadratic energy function. A simple test (essentially a vector by matrix multiplication) for checking for asymptotically stable equilibrium points is also provided. Finally, a special case of the generalized BSB model is shown to be applicable to a particular type of optimal control problem. © 1993 Academic Press. All rights reserved.
引用
收藏
页码:282 / 298
页数:17
相关论文
共 19 条
[1]  
ACKLEY DH, 1985, COGNITIVE SCI, V9, P147
[2]   DISTINCTIVE FEATURES, CATEGORICAL PERCEPTION, AND PROBABILITY-LEARNING - SOME APPLICATIONS OF A NEURAL MODEL [J].
ANDERSON, JA ;
SILVERSTEIN, JW ;
RITZ, SA ;
JONES, RS .
PSYCHOLOGICAL REVIEW, 1977, 84 (05) :413-451
[3]  
ANDERSON JA, 1986, SPIE ADV I OPTICAL H
[4]  
BARTO AG, 1989, P NSF WORKSHOP APPLI
[5]   ABSOLUTE STABILITY OF GLOBAL PATTERN-FORMATION AND PARALLEL MEMORY STORAGE BY COMPETITIVE NEURAL NETWORKS [J].
COHEN, MA ;
GROSSBERG, S .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1983, 13 (05) :815-826
[7]  
GOLDEN RM, 1986, COGNITIVE SCI, V10, P241
[8]  
GOLDEN RM, IN PRESS DISCOURSE P
[9]  
GOLDEN RM, 1991, 13TH P ANN C COGN SC
[10]   EQUILIBRIA OF THE BRAIN-STATE-IN-A-BOX (BSB) NEURAL MODEL [J].
GREENBERG, HJ .
NEURAL NETWORKS, 1988, 1 (04) :323-324