Improved Learning of Neural Nets Through Global Search
作者： V. P. Plagianakos , G. D. Magoulas , M. N. Vrahatis
关键词: Computer science 、 Machine learning 、 Process (engineering) 、 Simulated annealing 、 Artificial intelligence 、 Maxima and minima 、 Swarm intelligence 、 Minification 、 Artificial neural network 、 Evolutionary algorithm 、 Local search (optimization)
摘要: Learning in artificial neural networks is usually based on local minimization methods which have no mechanism that allows them to escape the influence of an undesired minimum. This chapter presents strategies for developing globally convergent modifications search and investigates use popular global network learning. The proposed tend lead desirable weight configurations allow learn entire training set, and, sense, they improve efficiency learning process. Simulation experiments some notorious their minima problems are presented extensive comparison several algorithms provided.
springer.com
sci-hub.se 参考文章(61)
Roberto Battiti, Accelerated Backpropagation Learning: Two Optimization Methods. Complex Systems. ,vol. 3, ,(1989)
G. D. Magoulas, M. N. Vrahatis, T. N. Grapsa, G. S. Androulakis, Neural network supervised training based on a dimension reducing method international conference on mathematics of neural networks models algorithms and applications models algorithms and applications. pp. 245- 249 ,(1997) , 10.1007/978-1-4615-6099-9_41
Terrence J. Sejnowski, Geoffrey E. Hinton, David Touretzsky, Proceedings of the 1988 Connectionist Models Summer School M. Kaufmann. ,(1989)
Nikos E. Mastorakis, Recent advances in circuits and systems World Scientific. ,(1998)
Vassilis P. Plagianakos, Michael N. Vrahatis, Parallel evolutionary training algorithms for “hardware-friendly“ neural networks Natural Computing. ,vol. 1, pp. 307- 322 ,(2002) , 10.1023/A:1016545907026
John H. Holland, Adaptation in natural and artificial systems ,(1992)
Elijah Polak, Optimization: Algorithms and Consistent Approximations ,(1997)
Christopher R Houck, Jeff Joines, Michael G Kay, A Genetic Algorithm for Function Optimization: A Matlab Implementation ,(2001)
Michael N. Vrahatis, George D. Magoulas, Vassilis P. Plagianakos, Globally Convergent Modification of the Quickprop Method Neural Processing Letters. ,vol. 12, pp. 159- 170 ,(2000) , 10.1023/A:1009661729970
Russ Eberhart, Pat Simpson, Roy Dobbins, None, Computational intelligence PC tools ,(1996)