An Enhanced Online Sequential Extreme Learning Machine algorithm

In this paper, an enhanced online sequential extreme learning machine (EOS-ELM) algorithm for single-hidden layer feedforward neural networks (SLFNs) with radial basis function (RBF) hidden nodes is proposed. The proposed EOS-ELM algorithm is an enhanced version of the OS-ELM of [8], which has been shown to be extremely fast with generalization performance better than other sequential training methods. The EOS-ELM algorithm adapts the node location, adjustment and pruning method of the MRAN of [3], so that the number of hidden nodes used in the OS-ELM can be modified. Simulation results show that the generalization performance of EOS-ELM is comparable to the OS-ELM and the number of nodes used by the EOS-ELM is reduced significantly.

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

[2]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[3]  Visakan Kadirkamanathan,et al.  A Function Estimation Approach to Sequential Learning with Neural Networks , 1993, Neural Computation.

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

[5]  Guang-Bin Huang,et al.  Learning capability and storage capacity of two-hidden-layer feedforward networks , 2003, IEEE Trans. Neural Networks.

[6]  Narasimhan Sundararajan,et al.  An efficient sequential learning algorithm for growing and pruning RBF (GAP-RBF) networks , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[7]  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).

[8]  Guang-Bin Huang,et al.  Classification ability of single hidden layer feedforward neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[9]  Samy Bengio,et al.  A Parallel Mixture of SVMs for Very Large Scale Problems , 2001, Neural Computation.

[10]  John C. Platt.  A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.

[11]  Y Lu,et al.  A Sequential Learning Scheme for Function Approximation Using Minimal Radial Basis Function Neural Networks , 1997, Neural Computation.

[12]  Guang-Bin Huang,et al.  Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions , 1998, IEEE Trans. Neural Networks.