Abstract
A hybrid algorithm for determining Radial Basis Function (RBF) networks is proposed. Evolutionary learning is applied to the non-linear problem of determining RBF network architecture (number of hidden layer nodes, basis function centres and widths) in conjunction with supervised gradient-based learning for tuning connection weights. A direct encoding of RBF hidden layer node basis function centres and widths is employed. The genetic operators utilised are adapted from those used in recent work on evolution of fuzzy inference systems. A parsimonious allocation of training sets and training epochs to evaluation of candidate networks during evolution is proposed in order to accelerate the learning process.
Keywords
- Radial Basis Function
- Hide Node
- Fuzzy Inference System
- Crossover Operator
- Radial Basis Function Neural Network
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Broomhead D.S. and Lowe D., Multivariable functional interpolation and adaptive networks. Complex Systems 2, 321–355, 1988.
Poggio T. and Girosi F., Networks for approximation and learning. Proceedings of the IEEE 78, 1481–1497, 1990.
Poggio T. and Edelman S., A network that learns to recognise three-dimensional objects. Nature (London) 343, 263–266, 1990.
Ng K. and Lippmann R.P., Practical characteristics of neural network and conventional pattern classifiers. In Advances in Neural Information Processing Systems 3 (Lippmann R.P., Moody J.E. and Touretzky D.S., eds) pp 970–976. San Mateo, CA: Morgan Kaufmann, 1991.
Moody J.E. and Darken C.J., Fast learning in networks of locally-tuned processing units. Neural Computation 1, 281–294, 1989.
Kassam S.A. and Cha I., Radial basis function networks in nonlinear signal processing applications. In Proceedings of the 27th Annual Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, 1993.
Haykin S. Neural Networks. Macmillan College Publishing Company, NewYork, NY, 1994.
Gruau F., Genetic synthesis of modular neural networks. In Forrest S. (ed.) Proceedings of the 5th International Conference on Genetic Algorithms, San Mateo CA, pp 318–325, 1993.
Cybenko G., Approximation by superposition of a sigmoidal function. Mathematics of Control, Signals and Systems 2, 303–314, 1989.
Park J. and Sandberg I. W., Universal approximation using radial-basis-function networks. Neural Computations, 246–257, 1991.
Schaffer J.D., Whitley D. and Eschelman L.J., Combinations of genetic algorithms and neural networks: a survey of the state of the art. In Proceedings of the International Workshop on Combinations of Genetic Algorithms and Neural Networks (COGANN-92), IEEE, pp1–37, 1992.
Yao X., A review of evolutionary artificial neural networks. International Journal of Intelligent Systems, 8, pp539–567, 1993
Whitley D, Genetic algorithms and neural networks. In Whiter G., Périaux J., Galán M. and Cuesta P. (eds) Genetic Algorithms in Engineering and Computer Science, pp203–216 Wiley, 1995.
Miller G.F., Todd P.M., Hegde S.U., Designing neural networks using genetic algorithms. Complex Systems 4, pp461–476, 1990.
Angeline P.J., Saunders G.M. and Pollack J.B., An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5, 1, pp54–65, January 1994.
Davidor Y., Epistatic variance: suitability of a representation to genetic algorithms. Complex Systems, 4, pp369–383, 1990.
Whitehead B.A. and Choate T.D., Evolving space-filling curves to distribute radial basis functions over an input space. IEEE Transactions on Neural Networks, 5, 1, pp 15–23, January 1994.
Chen S., Wu Y. and Alkadhimi K., A two-layer learning method for radial basis function networks using combined genetic and regularised OLS algorithms. In Proceedings of the 1st IEE/IEEE International Conference on Genetic Algorithms in Engineering Systems: Innovations and Applications, pp245–249, 1995.
Neruda R., Functional equivalence and genetic learning of RBF networks. In Pearson D.W., Steele N.C. and Albrecht R.F. (eds) Artificial Neural Nets and Genetic Algorithms, pp53–56, Springer-Verlag, 1995.
Hecht-Nielson R., On the algebraic structure of feed-forward network weight spaces. In Advanced Neural Computers, pp129–135, Elsevier, 1990
Jang J.R. and Sun C.T. (1993). Functional equivalence between radial basis function networks and fuzzy inference systems. IEEE Transactions on Neural Networks,4,1. pp156–159.
Carse B. and Fogarty T.C. (1994). A fuzzy classifier system using the Pittsburgh approach. In Davidor Y., Schwefel H.P. and Männer (eds) PPSN III-Proceedings of the International Conference on Evolutionary Computation, pp260–269. Springer-Verlag Berlin Heidelberg.
Carse B., Fogarty T.C. and Munro A., Evolving fuzzy rule based controllers using genetic algorithms. To appear in Fuzzy Sets and Systems, 1996.
Beasley D., Bull D.R., and Martin R.R., Complexity reduction using expansive coding. In Fogarty T.C. (ed) Post-Workshop Proceedings of the 1994 AISB Workshop on Evolutionary Computation, Lecture Notes in Computer Science #865, Springer-Verlag, pp304–319, 1994.
Carse B., Pipe A.G., Fogarty T.C. and Hill T., Evolving radial basis function neural networks using a genetic algorithm, Proceedings of the 2nd IEEE International Conference on Evolutionary Computation, 1995.
Mackey M.C. and Glass L., Oscillation and chaos in physiological control systems, Science vol. 197, pp287–289, 1977.
Goldberg D.E., Real-coded genetic algorithms, virtual alphabets, and blocking, Complex Systems vol. 5, pp139–167, 1991.
Robbins H. and Munroe S., A Stochastic approximation method, Annals of Mathematical Statistics 22, pp400–407, 1951.
Darken C. and Moody J., Towards faster stochastic gradient search, Advances in Neural Information Processing Systems 4, Moody J.E., Hanson S.J. and Lippmann (eds.), pp1009–1016, San Mateo, CA: Morgan Kaufmann, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Carse, B., Fogarty, T.C. (1996). Fast evolutionary learning of minimal radial basis function neural networks using a genetic algorithm. In: Fogarty, T.C. (eds) Evolutionary Computing. AISB EC 1996. Lecture Notes in Computer Science, vol 1143. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032769
Download citation
DOI: https://doi.org/10.1007/BFb0032769
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61749-5
Online ISBN: 978-3-540-70671-7
eBook Packages: Springer Book Archive