An algorithm for fast convergence in training neural networks
作者： B.M. Wilamowski , S. Iplikci , O. Kaynak , M.O. Efe
DOI: 10.1109/IJCNN.2001.938431
关键词: Jacobian matrix and determinant 、 Newton's method 、 Artificial neural network 、 Algorithm 、 Rate of convergence 、 Stochastic process 、 Levenberg–Marquardt algorithm 、 Computer science 、 Mathematical optimization 、 Feedforward neural network 、 Convergence (routing)
摘要: … -Marquardt algorithm for feedforward neural networks are studied. One … The modified algorithm gives a better convergence rate … The performance of the algorithm has been checked on …
linuxfocus.org 
researchgate.net 参考文章(17)
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams, Learning representations by back-propagating errors Nature. ,vol. 323, pp. 696- 699 ,(1988) , 10.1038/323533A0
Karthik Balakrishnan, Vasant Honavar, Improving Convergence of Back-Propagation by Handling Flat-Spots in the Output Layer international conference on artificial neural networks. pp. 1003- 1009 ,(1992) , 10.1016/B978-0-444-89488-5.50039-7
Sara A. Solla, Esther Levin, Michael Fleisher, Accelerated learning in layered neural networks Complex Systems. ,vol. 2, pp. 625- 639 ,(1988)
M.G. Bello, Enhanced training algorithms, and integrated training/architecture selection for multilayer perceptron networks IEEE Transactions on Neural Networks. ,vol. 3, pp. 864- 875 ,(1992) , 10.1109/72.165589
Roberto Battiti, First- and second-order methods for learning: between steepest descent and Newton's method Neural Computation. ,vol. 4, pp. 141- 166 ,(1992) , 10.1162/NECO.1992.4.2.141
C. Charalambous, A conjugate Gradient Algorithm for the Efficient Training of Artificial Neural Networks IEE Proceedings G Circuits, Devices and Systems. ,vol. 139, pp. 301- 310 ,(1990) , 10.1049/IP-G-2.1992.0050
Alessandro Sperduti, Antonina Starita, Speed up learning and network optimization with extended back propagation Neural Networks. ,vol. 6, pp. 365- 383 ,(1993) , 10.1016/0893-6080(93)90004-G
Frank Bärmann, Friedrich Biegler-König, Original Contribution: On a class of efficient learning algorithms for neural networks Neural Networks. ,vol. 5, pp. 139- 144 ,(1992) , 10.1016/S0893-6080(05)80012-7
S. Shah, F. Palmieri, MEKA-a fast, local algorithm for training feedforward neural networks 1990 IJCNN International Joint Conference on Neural Networks. pp. 41- 46 ,(1990) , 10.1109/IJCNN.1990.137822
A. Van Ooyen, B. Nienhuis, Improving the convergence of the back-propagation algorithm Neural Networks. ,vol. 5, pp. 465- 471 ,(1992) , 10.1016/0893-6080(92)90008-7