Canonical Genetic Learning of RBF Networks Is Faster
We extend our previous theoretical results concerning functional equivalence of Gaussian RBF networks and test the proposed canonical genetic learning algorithm on two problems. In our experiments, canonical learning achieved the same error threshold about two times faster in comparison to standard GA.
KeywordsRadial Basis Function Network Hide Unit Error Threshold Previous Theoretical Result Threshold canonIcal
Unable to display preview. Download preview PDF.
- R. Hecht-Nielsen. On the algebraic structure of feedforward network weight spaces. In Advanced Neural Computers, pages 129–135. Elsevier, 1990.Google Scholar
- K. Hlaváčková and R. Neruda. Radial basis function networks. Neural Network World, (1):93–101, 1993.Google Scholar
- V. Kurkova and R. Neruda. Uniqueness of the functional representations for the gaussian basis functions. In Proceedings of the ICANN’94, pages 474–477, London, 1994. Springer.Google Scholar
- R. Neruda. Functional equivalence and genetic learning of RBF networks. In D.W. Pearson, N. C. Steele, R.F. Albrecht (editors), Artificial Neural Networks and Genetic Algorithms, pages 53–56, Wien New York, 1995. Springer Verlag.Google Scholar