Convergence of batch gradient algorithm for feedforward neural network training

Journal of Information and Computational Science

Volumn 4, Issue 1, 2007, Pages 251-255

  Shao, Hongmei ^a   Wu, Wei ^a   Li, Feng ^a   Zheng, Gaofeng ^a  

^a DALIAN UNIVERSITY OF TECHNOLOGY   (China)

Author keywords

Convergence; Feedforward neural network; Gradient algorithm

Indexed keywords

CONVERGENCE OF NUMERICAL METHODS; ERRORS; FUNCTIONS; ITERATIVE METHODS; LEARNING ALGORITHMS; OPTIMIZATION;

GRADIENT ALGORITHMS; LEARNING RATE; MONOTONICITY ERROR FUNCTIONS; TRAINING ITERATION; WEIGHTS TRAINING;

FEEDFORWARD NEURAL NETWORKS;

EID: 34547738577     PISSN: 15487741     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (8)

1. L. Armijo, Minimization of functions having Lipschitz continuous first partial derivatives, Pacific J. Math. 16 (1966) 1-3.
2. A. A. Goldstein, Caucby's method of minimization, Numer. Math. 4 (1962) 146-150.
3. M. T. Hagan, H. B. Demuth and M. Beale, Neural Network Design, China Machine Press, second edition, 2003.
4. D. E. Rumelhart, J. L. McClelland and the PDP Research Group, Parallel Distributed Processing-Explorations in the Microstructure of Cognition, Mass., MIT Press, Cambridge, 1986.
5. W. Wu, Computation of Neural Networks, Higher Education Press, Beijing, 2003.
6. W. Wu, G. R. Feng and X. Li, Training multilayer perceptrons via minimization of sum of ridge functions, Advances in Computational Mathematics 17 (2002) 331-347.
7. D. R. Wilson and T. R. Martinez, The need for small learning rates on large problems, in: IJCNN'01, 2001, pp. 115-119.
8. Y. X. Yuan and W. Y. Sun, Optimization Theory and Methods, Science Press, Beijing, 2001.