Keywords

evolutionary computation, neural networks, training sets

Abstract

Training Set Evolution is an eclectic optimization technique that combines evolutionary computation (EC) with neural networks (NN). The synthesis of EC with NN provides both initial unsupervised random exploration of the solution space as well as supervised generalization on those initial solutions. An assimilation of a large amount of data obtained over many simulations provides encouraging empirical evidence for the robustness of Evolutionary Training Sets as an optimization technique for feedback and control problems.

Original Publication Citation

Ventura, D. and Martinez, T. R., "Robust Optimization Using Training Set Evolution", Proceedings of the ICNN'96 IEEE International Conference on Neural Networks, pp. 524-528, 1996.

Document Type

Peer-Reviewed Article

Publication Date

1996-06-06

Permanent URL

http://hdl.lib.byu.edu/1877/2438

Publisher

IEEE

Language

English

College

Physical and Mathematical Sciences

Department

Computer Science

Share

COinS