Extreme Reformulated Radial Basis Function Neural Networks

Gradient descent based learning algorithms are generally very slow due to improper learning steps or may easily converge to local minima. And many iterative learning steps may be required by such learning algorithms in order to obtain better learning performance. This paper proposes a new learning algorithm for R-RBFNs which randomly chooses hidden nodes and analytically determines the output weights of R-RBFNs. The experimental results based on a few benchmark problems has shown that the proposed algorithm tends to provide better generalization performance at extremely fast learning speed.

[1]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

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

[3]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

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

[5]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[6]  Nicolaos B. Karayiannis,et al.  On the construction and training of reformulated radial basis function neural networks , 2003, IEEE Trans. Neural Networks.

[7]  Nicolaos B. Karayiannis,et al.  Reformulated radial basis neural networks trained by gradient descent , 1999, IEEE Trans. Neural Networks.

[8]  Hong Chen,et al.  Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks , 1993, IEEE Trans. Neural Networks.

[9]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[10]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[11]  Narasimhan Sundararajan,et al.  On-Line Sequential Extreme Learning Machine , 2005, Computational Intelligence.

[12]  C. Micchelli.  Interpolation of scattered data: Distance matrices and conditionally positive definite functions , 1986 .