From Evolutionary Computation to Natural Computation
Evolutionary computation has enjoyed a tremendous growth in more than a decade in both its theoretical foundations and industrial applications. Its scope has gone beyond its earlier meaning of “genetic evolution”. Many research topics in evolutionary computation nowadays are not necessarily “evolutionary” in any sense. There is a need for studying a wide variety of nature inspired computational algorithms and techniques, including evolutionary, neural, ecological computation, etc., in a unified framework This paper gives an overview of some work that has been going on in the Natural Computation Group at The University of Birmingham, UK. It covers topics in optimisation, learning and design using nature inspired algorithms and techniques. Some recent theoretical results in the computational time complexity of evolutionary and neural optimisation algorithms will also be mentioned.
KeywordsEvolutionary Computation Neural Network Ensemble Drift Condition Gaussian Mutation Negative Correlation Learning
Unable to display preview. Download preview PDF.
- X. Yao, “An overview of evolutionary computation,” Chinese Journal of Advanced Software Research (Allerton Press, Inc., New York, NY 10011), vol. 3, no. 1, pp. 12–29, 1996.Google Scholar
- D. B. Fogel, System Identification Through Simulated Evolution: A Machine Learning Approach to Modeling. Needham Heights, MA 02194: Ginn Press, 1991.Google Scholar
- D. B. Fogel, Evolving Artificial Intelligence. PhD thesis, University of California, San Diego, CA, 1992.Google Scholar
- R. A. Hunt, Calculus with Analytic Geometry. New York, NY 10022-5299: Harper & Row Publ., Inc., 1986.Google Scholar
- O. G. Selfridge, “Pandemonium: a paradigm for learning,” in Mechanisation of Thought Processes: Proc. of a Symp. Held at the National Physical Lab., pp. 513–526, HMSO, London, 1958.Google Scholar
- Y. Liu and X. Yao, “Negatively correlated neural networks can produce best ensembles,” Australian Journal of Intelligent Information Processing Systems, vol. 4, no. 3/4, pp. 176–185,1997.Google Scholar
- Y. Liu and X. Yao, “A cooperative ensemble learning system,” in 1998 IEEE International Joint Conference on Neural Networks, Anchorage, USA, (Piscataway, NJ, USA), pp. 2202–2207, IEEE Press, 1998.Google Scholar
- Y. Liu and X. Yao, “Towards designing neural network ensembles by evolution,” in Parallel Problem Solving from Nature (PPSN) V (A. E. Eiben, T. Back, M. Schoenauer, and H.-P. Schwefel, eds.), vol. 1498 of Lecture Notes in Computer Science, (Berlin), pp. 623–632, Springer-Verlag, 1998.Google Scholar
- D. B. Fogel, Evolutionary Computation: Towards a New Philosophy of Machine Intelligence. New York, NY: IEEE Press, 1995.Google Scholar
- X. Yao, ed., Evolutionary Computation: Theory and Applications. Singapore: World Scientific Publishing Co., 1999.Google Scholar