A new learning algorithm for function approximation incorporating a priori information into extreme learning machine

Authors:
Fei Han;Tat-Ming Lok;Michael R. Lyu
Affiliations:
Intelligent Computing Lab, Hefei Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, Anhui, China;Information Engineering Dept., The Chinese University of Hong Kong, Shatin, Hong Kong;Computer Science & Engineering Dept., The Chinese University of Hong Kong, Shatin, Hong Kong
Venue:
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Year:
2006

Citing 7
Cited 1

What size net gives valid generalization?

Neural Computation
Merging back-propagation and Hebbian learning rules for robust classifications

Neural Networks
A neural root finder of polynomials based on root moments

Neural Computation
A new modified hybrid learning algorithm for feedforward neural networks

ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
A constructive approach for finding arbitrary roots of polynomials by neural networks

IEEE Transactions on Neural Networks
Magnified gradient function with deterministic weight modification in adaptive learning

IEEE Transactions on Neural Networks
An efficient constrained training algorithm for feedforward networks

IEEE Transactions on Neural Networks

Improved Learning Algorithms of SLFN for Approximating Periodic Function

ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a new algorithm for function approximation is proposed to obtain better generalization performance and faster convergent rate. The new algorithm incorporates the architectural constraints from a priori information of the function approximation problem into Extreme Learning Machine. On one hand, according to Taylor theorem, the activation functions of the hidden neurons in this algorithm are polynomial functions. On the other hand, Extreme Learning Machine is adopted which analytically determines the output weights of single-hidden layer FNN. In theory, the new algorithm tends to provide the best generalization at extremely fast learning speed. Finally, several experimental results are given to verify the efficiency and effectiveness of our proposed learning algorithm.