Neural Network Based Algorithm for Dynamic System Optimization

A class of artificial neural networks with a two-layer feedback topology to solve nonlinear discrete dynamic optimization problems is developed. Generalized recurrent neuron models are introduced. A direct method to assign the weights of neural networks is presented. The method is based on Bellmann's Optimality Principle and on the interchange of information which occurs during the synaptic chemical processing among neurons. A comparative analysis of the computational requirements is made. The analysis shows advantages of this approach as compared to the standard dynamic programming algorithm. The technique has been applied to several important optimization problems, such as shortest path and control optimal problems.

[1]  Donald E. Kirk,et al.  Optimal control theory : an introduction , 1970 .

[2]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[3]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  F. Gomide,et al.  A neural network for N-stage optimal control problems , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[5]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[6]  K. F. Fong,et al.  Discrete-time optimal control using neural nets , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[7]  Richard S. Sutton,et al.  Reinforcement Learning is Direct Adaptive Optimal Control , 1992, 1991 American Control Conference.

[8]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[9]  Panos J. Antsaklis,et al.  Neural networks for control systems , 1990, IEEE Trans. Neural Networks.

[10]  Kumpati S. Narendra,et al.  Neural networks in control systems , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[11]  R. Bellman.  Dynamic programming. , 1957, Science.

[12]  Marco Tomassini,et al.  A phylogenetic, ontogenetic, and epigenetic view of bio-inspired hardware systems , 1997, IEEE Trans. Evol. Comput..

[13]  C.-H. Wu,et al.  Voluntary movements for robotic control , 1992, IEEE Control Systems.

[14]  A. F. Da Rocha,et al.  Neural Nets: A Theory for Brains and Machines , 1992 .

[15]  Richard Bellman,et al.  Decision-making in fuzzy environment , 2012 .

[16]  M. Wells,et al.  Learning with delayed rewards in Octopus , 1968, Zeitschrift für vergleichende Physiologie.

[17]  B. Widrow,et al.  Neural networks for self-learning control systems , 1990, IEEE Control Systems Magazine.

[18]  Thomas Parisini,et al.  Backpropagation for N-stage optimal control problems , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[19]  Janusz Kacprzyk,et al.  Multistage evolutionary optimization of fuzzy systems—application to optimal fuzzy control , 1997 .

[20]  Rajkumar Roy,et al.  Advances in Soft Computing , 2018, Lecture Notes in Computer Science.

[21]  Andrew G. Barto,et al.  Learning to Act Using Real-Time Dynamic Programming , 1995, Artif. Intell..

[22]  Minoru Fukumi,et al.  A new back-propagation algorithm with coupled neuron , 1991, International 1989 Joint Conference on Neural Networks.

[23]  Fernando Gomide,et al.  A neural network for fuzzy decision making problems , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[24]  Fernando Gomide,et al.  Neurofuzzy Components based on Threshold , 1992 .

[25]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[26]  C.W. Anderson,et al.  Learning to control an inverted pendulum using neural networks , 1989, IEEE Control Systems Magazine.