A Fate of Two Evolutionary Walkers after the Departure from the Origin
Using Sammon mappings, a method to visualize multidimensional space, we observe a strange difference between two evolutionary searches: Evolutionary Programming and Breeder Genetic Algorithm, when they search for weight solutions of fully connected neural network model of associative memory.
KeywordsNeural Network Model Synaptic Weight Pattern Space Evolutionary Search Uniform Crossover
Unable to display preview. Download preview PDF.
- Collins, T. D. (1997) Using Software Visualization Technology to Help Evolutionary Algorithm Users Validate their Solutions. Proceedings of the 7th International Conference on Genetic Algorithms, pp.307–314.Google Scholar
- Gardner, E. (1988) The Phase Space of Interactions in Neural Network Models. Journal of Physics, 21A, pp. 257–270.Google Scholar
- Hopfield, J. J. (1982) Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proc. of the National Academy of Sciences, USA 79, pp. 2554–2558.Google Scholar
- Hebb, D. O. (1949) The Organization of Behavior. Wiley.Google Scholar
- Komlós, J., and R. Paturi (1988) Convergence Results in an Associative Memory Model. Neural Networks 1, pp. 239–250.Google Scholar
- Sammon, J. W. (1969) A Nonlinear Mapping for Data Structure Analysis. IEEE Transactions on Computers. C-18(5), pp.401–408.Google Scholar
- Shine, W. B. and C. F. Eick (1997) Visualizing the Evolution of Genetic Algorithm Search Processes. Proceedings of the IEEE International Conference on Evolutionary Computation, pp.367–372.Google Scholar
- Syswerda, G. (1989) Uniform Crossover in Genetic Algorithms. Proceedings of the 3rd International Conference on Genetic Algorithms, pp.2–9.Google Scholar