期刊文献+

自适应递阶遗传算法优化BP网络的程序设计 被引量:3

Program Design of BP Network Optimized by Adaptive Hierarchical Genetic Algorithm
下载PDF
导出
摘要 主要阐述了一种新的遗传算法-自适应递阶遗传算法的基本原理,解决了长期以来无法同时对神经网络拓扑结构和神经网络的权值和阈值进行优化的问题,设计了一个基于自适应递阶遗传算法的BP神经网络学习算法,给出了具体的程序设计,并且利用MATLAB平台进行仿真计算.实验结果表明,该算法比一般遗传算法具有明显的优越性,可以避免神经网络陷入局部最优,迅速优化网络的拓扑结构,提高了网络的学习性能,具有一定的实用性。 The paper proposes the basic principle of a new genetic algorithm adaptive hierarchical genetic algorithm (AHGA), solves the problem of optimizing the structure and the weights of neural network simultaneously, and gives the specific program design, The result of experiment based on MATLAB indicates that AHGA algorithm has superiority over simple genetic algorithm (SGA), It can avoid the disadvantages of BP algorithm ,optimize the structure of network quickly, improve the learning performance of network.
出处 《计算机仿真》 CSCD 2007年第8期159-162,共4页 Computer Simulation
基金 国家十五攻关子课题(2004BA204B08-03)
关键词 神经网络 自适应递阶遗传算法 优化 Neural network Adaptive hierarchical genetic algorithm Optimization
  • 相关文献

参考文献4

二级参考文献19

  • 1唐飞,滕弘飞.十进制整数编码遗传算法的模式定理研究[J].计算机科学,1999,26(6):54-56. 被引量:6
  • 2蔡正国,屈梁生.共轭梯度神经网络的研究[J].西安交通大学学报,1995,29(8):72-76. 被引量:11
  • 3W Schiffmann, M Joost, R Werner. Optimization of the Backpropagation Algorithm for Trining Multilayer Perceptrons Technical Report[ R].University of Koblenz, Institute of Physics, 1993.
  • 4Hecht- Nielsen R. Theory of Backpropagation Neural Networks[ C ].Proc. IJCNN - 89.1989. 1-593.
  • 5R P Lippmann. Pattern Classification using Neural Networks[ J]. IEEE Comm , Magazine, Nov. 1989,47-64.
  • 6S Y Kung, J N Hwang. An Algebraic Projection Analysis for Optional Hidden Units Size and Learning Rates in Back - Propagation Learning[J]. IEEE, 1991, I: 363 - 370.
  • 7S Y Kung, Hu Yu Hen. A Frobenius Approximation Reduction(FARM)for Determining Optimal Number of Hidden Units[J]. IEFE, 1991, Ⅱ:163 - 168.
  • 8M T Hagan, M B Mangis. Training Feed Forward Networks with Marquart Alogrithm[J]. IEEE Trans.on Neural Networks, 1994,5(6):989-993.
  • 9T P Vogl, J K Mangis, ect. Accelerated the Convergence of the Back Propagation Method [ J ]. Bio. Cybern, 1988,59 (9): 256 - 264.
  • 10J H Holland.Adapation in Natural and Artifical Systems.Ann Arbor,MI:University Michigan Press,1975.

共引文献6

同被引文献24

引证文献3

二级引证文献56

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部