What size net gives valid generalization?
Neural Computation
A neural root finder of polynomials based on root moments
Neural Computation
ISNN'06 Proceedings of the Third 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
A Group Selection Evolutionary Extreme Learning Machine approach for Time-Variant Neural Networks
Proceedings of the 2011 conference on Neural Nets WIRN10: Proceedings of the 20th Italian Workshop on Neural Nets
| Hi-index | 0.00 |
In this paper, three improved Extreme Learning Machines (ELMs) are proposed to approximating periodic function. According to Fourier series expansion theory, the hidden neurons activation functions in the improved ELM are a class of sine and cosine functions. In addition, the improved ELM analytically determines the output weights of neural networks. In theory, the new algorithm tends to provide the best approximation performance at extremely fast learning speed. The proposed ELMs have better approximation accuracies and faster convergence rate than traditional ELM and gradient-based learning algorithms. Finally, experimental results are given to verify the efficiency and effectiveness of the proposed ELMs.