Investigation of Neural Networks for Function Approximation

In this work, some ubiquitous neural networks are applied to model the landscape of a known problem function approximation. The performance of the various neural networks is analyzed and validated via some well-known benchmark problems as target functions, such as Sphere, Rastrigin, and Griewank functions. The experimental results show that among the three neural networks tested, Radial Basis Function (RBF) neural network is superior in terms of speed and accuracy for function approximation in comparison with Back Propagation (BP) and Generalized Regression Neural Network (GRNN).

[1]  Eng-Chong Tan,et al.  An integrated approach to improving back-propagation neural networks , 1994, Proceedings of TENCON'94 - 1994 IEEE Region 10's 9th Annual International Conference on: 'Frontiers of Computer Technology'.

[2]  Jun Gao,et al.  A survey of neural network ensembles , 2005, 2005 International Conference on Neural Networks and Brain.

[3]  Tarun Varshney,et al.  Approximation of 2D function using simplest neural networks — A comparative study and development of GUI system , 2010, 2010 International Conference on Power, Control and Embedded Systems.

[4]  Jayadeva,et al.  Algorithm for building a neural network for function approximation , 2002 .

[6]  R. Setiono,et al.  Neural network pruning for function approximation , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[7]  Bram van Heuveln,et al.  The normalized radial basis function neural network , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[8]  Robert F. Stengel,et al.  Smooth function approximation using neural networks , 2005, IEEE Transactions on Neural Networks.

[9]  Leorey Marquez,et al.  Function approximation using backpropagation and general regression neural networks , 1993, [1993] Proceedings of the Twenty-sixth Hawaii International Conference on System Sciences.

[10]  R. Yusof,et al.  Nonlinear function approximation using radial basis function neural networks , 2002, Student Conference on Research and Development.

[11]  Chein-I Chang,et al.  A sigmoidal radial basis function neural network for function approximation , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[12]  Lijuan Yu,et al.  Study on fitness data processing based on neural network information processing , 2012, 2012 International Conference on Systems and Informatics (ICSAI2012).

[13]  Ching-Shiow Tseng,et al.  An orthogonal neural network for function approximation , 1996, IEEE Trans. Syst. Man Cybern. Part B.