A biologically inspired neural network for dynamic system optimization

A neural network with a two-layer feedback topology and generalized recurrent neurons, for solving nonlinear discrete dynamic optimization problems is developed. The algorithm is based on R. Bellmann's (1957) optimality principle and the interchange of information during synaptic chemical processing among neurons. The technique is applied to solve fuzzy decision making problems.

[1]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

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

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

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

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

[6]  Ronald R. Yager,et al.  Essentials of fuzzy modeling and control , 1994 .

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

[8]  Roseli A. Francelin Romero,et al.  Involving objective and subjective aspects in multistage decision making and control under fuzziness: Dynamic programming and neural networks , 1999, Int. J. Intell. Syst..

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

[10]  John E. Hershey,et al.  Computation , 1991, Digit. Signal Process..

[11]  Fernando Gomide,et al.  Involving objective and subjective aspects in multistage decision making and control under fuzziness: Dynamic programming and neural networks , 1999 .

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