Fast Evolutionary Learning of Minimal Radial Basis Function Neural Networks Using a Genetic Algorithm

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.

[1]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[2]  John E. Moody,et al.  Towards Faster Stochastic Gradient Search , 1991, NIPS.

[3]  Saleem A. Kassam,et al.  Radial basis function networks in nonlinear signal processing applications , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[4]  Bruce A. Whitehead,et al.  Evolving space-filling curves to distribute radial basis functions over an input space , 1994, IEEE Trans. Neural Networks.

[5]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[6]  Xin Yao,et al.  A review of evolutionary artificial neural networks , 1993, Int. J. Intell. Syst..

[7]  J. D. Schaffer,et al.  Combinations of genetic algorithms and neural networks: a survey of the state of the art , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[8]  Yuval Davidor,et al.  Epistasis Variance: Suitability of a Representation to Genetic Algorithms , 1990, Complex Syst..

[9]  R. Hecht-Nielsen.  ON THE ALGEBRAIC STRUCTURE OF FEEDFORWARD NETWORK WEIGHT SPACES , 1990 .

[10]  Peter M. Todd,et al.  Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[11]  Chuen-Tsai Sun,et al.  Functional equivalence between radial basis function networks and fuzzy inference systems , 1993, IEEE Trans. Neural Networks.

[12]  Frédéric Gruau,et al.  Genetic Synthesis of Modular Neural Networks , 1993, ICGA.

[13]  Roman Neruda.  Functional Equivalence and Genetic Learning of RBF Networks , 1995, ICANNGA.

[14]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[15]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[16]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[17]  David E. Goldberg,et al.  Real-coded Genetic Algorithms, Virtual Alphabets, and Blocking , 1991, Complex Syst..

[18]  Alistair Munro,et al.  Evolving fuzzy rule based controllers using genetic algorithms , 1996, Fuzzy Sets Syst..

[19]  S. Chen,et al.  A two-layer learning method for radial basis function networks using combined genetic and regularised OLS algorithms , 1995 .

[20]  Ralph R. Martin,et al.  Complexity Reduction Using Expansive Coding , 1994, Evolutionary Computing, AISB Workshop.

[21]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[22]  Brian Carse,et al.  A Fuzzy Classifier System Using the Pittsburgh Approach , 1994, PPSN.

[23]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[24]  B. Carse,et al.  Evolving radial basis function neural networks using a genetic algorithm , 1995, Proceedings of 1995 IEEE International Conference on Evolutionary Computation.

[25]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.