论文信息 - Biological Evolution as a Paradigm for Performance Driven Design Processes

Biological Evolution as a Paradigm for Performance Driven Design Processes

The application of evolutionary processes to the problem of automated design is explored. A feature detector component for a pattern recognition system is used as an example of the automated design process. Results obtained from applying the resultant detector system to the problem of character recognition are discussed.

Louis A. Tamburino | Mateen M. Rizki | Michael A. Zmuda

[1] M. Rizki,et al. Computing the theory of evolution , 1986 .

[2] L.A. Tamburino,et al. Automated feature detection using evolutionary learning processes , 1989, Proceedings of the IEEE National Aerospace and Electronics Conference.

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

[4] Fred Stentiford,et al. Automatic Feature Design for Optical Character Recognition Using an Evolutionary Search Procedure , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5] Lawrence Davis,et al. Genetic Algorithms and Simulated Annealing , 1987 .

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

[7] E. Feigenbaum,et al. Computers and Thought , 1963 .

[8] L.A. Tamburino,et al. Automatic generation of binary feature detectors , 1989, IEEE Aerospace and Electronic Systems Magazine.

[9] Mateen M. Rizki,et al. Computational resource management in supervised learning systems , 1989, Proceedings of the IEEE National Aerospace and Electronics Conference.

[10] Andrew Mcgilvary Gillies,et al. Machine Learning Procedures for Generating Image Domain Feature Detectors , 1985 .

[11] Jean Serra,et al. Image Analysis and Mathematical Morphology , 1983 .