A mended hybrid learning algorithm for radial basis function neural networks to improve generalization capability

A two-step learning scheme for radial basis function neural networks, which combines the genetic algorithm (GA) with the hybrid learning algorithm (HLA), is proposed in this paper. It is compared with the methods of the GA, the recursive orthogonal least square algorithm (ROLSA) and another two-step learning scheme for RBF neural networks, which combines the K-means clustering with the HLA (K-means + HLA). Our proposed method has the best generalization performance.

[1]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[2]  Zhi-Hua Zhou,et al.  FANNC: A Fast Adaptive Neural Network Classifier , 2000, Knowledge and Information Systems.

[3]  De-Shuang Huang,et al.  Noise reduction in lidar signal based on discrete wavelet transform , 2004 .

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

[5]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[6]  Witold Pedrycz,et al.  Conditional fuzzy clustering in the design of radial basis function neural networks , 1998, IEEE Trans. Neural Networks.

[7]  Min-Soeng Kim,et al.  Nonlinear time series modelling and prediction using Gaussian RBF network with evolutionary structure optimisation , 2001 .

[8]  Andrei B. Utkin,et al.  Detection of small forest fires by lidar , 2002 .

[9]  Cuneyt Guzelis,et al.  Input-output clustering for determining centers of radial basis function network , 1997 .

[10]  J.D. Van Wyk,et al.  Optimal control of a hybrid power compensator using an artificial neural network controller , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).

[11]  De-shuang Huang,et al.  The structure optimization of radial basis probabilistic neural networks based on genetic algorithms , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[12]  Meng Joo Er,et al.  Face recognition with radial basis function (RBF) neural networks , 2002, IEEE Trans. Neural Networks.

[13]  Alvin M. Strauss,et al.  Weld modeling and control using artificial neural networks , 1993 .

[14]  Dingli Yu,et al.  Selecting radial basis function network centers with recursive orthogonal least squares training , 2000, IEEE Trans. Neural Networks Learn. Syst..

[15]  Mischa Reinhardt,et al.  Erratum: Corrigendum: Design of a genome-wide siRNA library using an artificial neural network , 2006, Nature Biotechnology.

[16]  H. Breusers,et al.  Applied Mathematical Modelling , 1976 .

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

[18]  Sukhan Lee,et al.  A Gaussian potential function network with hierarchically self-organizing learning , 1991, Neural Networks.

[19]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.