A Boltzmann machine for the organization of intelligent machines

A three-tier structure consisting of organization, coordination, and execution levels forms the architecture of an intelligent machine using the principle of increasing precision with decreasing intelligence from a hierarchically intelligent control. This system has been formulated as a probabilistic model, where uncertainty and imprecision can be expressed in terms of entropies. The optimal strategy for decision planning and task execution by the intelligent machine can be found by minimizing the total entropy in the system. The focus is on the design of the organization level of the intelligent machine as a Boltzmann machine, as described in current neural network literature. Since this level is responsible for planning the actions of the machine, the problem at this tier is formulated as the construction of the right sequence of tasks or events that minimizes the entropy for the desired action. The Boltzmann machine is reformulated to use entropy as the cost function to be minimized. Simulated annealing, expanding subinterval random search, and the genetic algorithm are presented as search techniques to efficiently find the desired action sequence. The genetic algorithm is modified to ensure convergence in probability to the minimum entropy of the system. Simulations of these algorithms are shown and performance is analyzed. >

[1]  Moshe Kam,et al.  On stable points and cycles in binary neural networks , 1987 .

[2]  Roger C. Conant,et al.  Laws of Information which Govern Systems , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  G. N. Saridis,et al.  Intelligent robotic control , 1983 .

[4]  D. Ackley.  A connectionist machine for genetic hillclimbing , 1987 .

[5]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

[6]  D. Whitteridge,et al.  Learning and Relearning , 1959, Science's STKE.

[7]  Kenneth Alan De Jong,et al.  An analysis of the behavior of a class of genetic adaptive systems. , 1975 .

[8]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[9]  George N. Saridis,et al.  Analytic formulation of the principle of increasing precision with decreasing intelligence for intelligent machines , 1988, Autom..

[10]  Frederick Hayes-Roth,et al.  Building expert systems , 1983, Advanced book program.

[11]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  G. Zames.  On the metric complexity of casual linear systems: ε -Entropy and ε -Dimension for continuous time , 1979 .

[13]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[14]  Alexander H. Levis.  Human organizations as distributed intelligence systems , 1988 .

[15]  Harry E. Stephanou,et al.  A Hierarchical Approach to the Control of a Prosthetic Arm , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[16]  Lawrence Davis,et al.  Genetic Algorithms and Communication Link Speed Design: Theoretical Considerations , 1987, ICGA.

[17]  Michael L. Mauldin,et al.  Maintaining Diversity in Genetic Search , 1984, AAAI.

[18]  George N. Saridis,et al.  Linguistic Decision Schemata for Intelligent Robots , 1981 .

[19]  G. N. Saridis,et al.  Analytic formulation of intelligent machines as neural nets , 1988, Proceedings IEEE International Symposium on Intelligent Control 1988.

[20]  G. Saridis.  Entropy formulation of optimal and adaptive control , 1988 .

[21]  Geoffrey E. Hinton,et al.  Massively Parallel Architectures for AI: NETL, Thistle, and Boltzmann Machines , 1983, AAAI.

[22]  David G. Luenberger,et al.  Linear and nonlinear programming , 1984 .

[23]  G.N. Saridis,et al.  Toward the realization of intelligent controls , 1979, Proceedings of the IEEE.

[24]  George N. Saridis.  Expanding subinterval random search for system identification and control , 1977 .

[25]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[26]  Kimon P. Valavanis,et al.  Analytical design of intelligent machines , 1985, Autom..

[27]  Dirk Van Gucht,et al.  Incorporating Heuristic Information into Genetic Search , 1987, International Conference on Genetic Algorithms.

[28]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[29]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[30]  John J. Grefenstette,et al.  Genetic Algorithms for the Traveling Salesman Problem , 1985, ICGA.