Acceleration of Levenberg-Marquardt Training of Neural Networks with Variable Decay Rate

Proceedings of the International Joint Conference on Neural Networks

Volumn 3, Issue , 2003, Pages 1873-1878

  Chen, Tai Cong ^a   Han, Da Jian ^a   Au, Francis T K ^b   Tham, L G ^b  

^a SOUTH CHINA UNIVERSITY OF TECHNOLOGY   (China)

^b UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; ITERATIVE METHODS; OSCILLATIONS; VARIATIONAL TECHNIQUES;

VARIABLE DECAY RATE;

NEURAL NETWORKS;

EID: 0141794666     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. M. T. Hagan and M. B. Menhaj, "Training feedforward networks with the Marquardt algorithm", IEEE Trans. on Neural Net., vol. 5, no. 6, pp. 989-993, 1994.
2. G. Zhou and J. Si, "Advanced neural-net work training algorithm with reduced complexity based on Jacobian deficiency", IEEE Trans. on Neural Net., vol. 9, no. 3, pp. 448-453, 1998.
3. L. W. Chan and C. C. Szeto, "Training recurrent network with block-diagonal approximated Levenberg-Marquardt algorithm", in Proc. IJCNN, vol. 3, pp. 1521-1526, 1999.
4. B. M. Wilamowski, Y. Chen, and A. Malinowski, "Efficient algorithm for training neural networks with one hidden layer", in Proc. IJCNN, vol. 3, pp. 1725-1728, 1999.
5. D. Marquardt, "An algorithm for least squares estimation of nonlinear parameters", J. Soc. Ind. Appl. Math., pp. 431-441, 1963.
6. H. Demuth and M. Beale, Neural Network TOOLBOX User's Guide. For use with MATLAB, The MathWorks Inc., 1998.
7. D. Nguyen and B. Widrow, "Improving the learning speed of 2-layer neural networks by choosing initial values of adaptive weights", in Proc. IJCNN, vol. 3, pp. 21-26, 1990.