Convergence of an online gradient method for BP neural networks with stochastic inputs

Authors:
Zhengxue Li;Wei Wu;Guorui Feng;Huifang Lu
Affiliations:
Department of Applied Mathematics, Dalian University of Technology, Dalian, China;Department of Applied Mathematics, Dalian University of Technology, Dalian, China;Mathematics Department, Shanghai Jiaotong University, Shanghai, China;Department of Applied Mathematics, Dalian University of Technology, Dalian, China
Venue:
ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
Year:
2005

Citing 7
Cited 1

Diffusion approximations for the constant learning rate backpropagation algorithm and resistance to local minima

Neural Computation
Pattern recognition using neural networks: theory and algorithms for engineers and scientists

Pattern recognition using neural networks: theory and algorithms for engineers and scientists
Parameter convergence and learning curves for neural networks

Neural Computation
Deterministic convergence of an online gradient method for neural networks

Journal of Computational and Applied Mathematics - Selected papers of the international symposium on applied mathematics, August 2000, Dalian, China
Convergence of an online gradient method for feedforward neural networks with stochastic inputs

Journal of Computational and Applied Mathematics - Special issue on proceedings of the international symposium on computational mathematics and applications
Convergence analysis of online gradient method for BP neural networks

Neural Networks
Optimal convergence of on-line backpropagation

IEEE Transactions on Neural Networks

When does online BP training converge?

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.04

Visualization

Abstract

An online gradient method for BP neural networks is presented and discussed. The input training examples are permuted stochastically in each cycle of iteration. A monotonicity and a weak convergence of deterministic nature for the method are proved.