期刊文献+

基于反传混沌粒子群训练的前馈神经网络研究 被引量:2

Research of training feedforward neural networks based on hybrid chaos particle swarm optimization-back-propagation
下载PDF
导出
摘要 为了解决前馈神经网络训练收敛速度慢、易陷入局部极值及对初始权值依赖性强等缺点,提出了一种基于反传的无限折叠迭代混沌粒子群优化(ICMICPSO)算法训练前馈神经网络(FNNs)参数。该方法在充分利用BP算法的误差反传信息和梯度信息的基础上,引入了ICMIC混沌粒子群的概念,将ICMIC粒子群(ICMICPS)作为全局搜索器,梯度下降信息作为局部搜索器来调整网络的权值和阈值,使得粒子能够在全局寻优的基础上对整个空间进行搜索。通过仿真实验与多种算法进行对比,结果表明在训练和泛化能力上ICMICPSO-BPNN方法明显优于其他算法。 In order to overcome the shortcomings of feedforward neural network's slow convergence, involving the local optimal and depending on the initial weights, this paper proposed a new method to train feedforward neural networks (FNNs) parameters based on the iterative chaotic map with infinite collapses particle swarm optimization(ICMICPSO)algorithm. This algorithm made full use of the information of BP's error back propagation and gradient. It used ICMICPS as the global optimizer to adjust the neural networks' weights and thresholds, when network parameters converge around global optimum. And it used gradient information as a local optimizer to accelerate the modification at a local scale. Compared with other algorithms, results show that the performance of the ICMICPSO-BPNN method is superior to the contrast methods in training and generalization ability.
出处 《计算机应用研究》 CSCD 北大核心 2014年第1期120-123,133,共5页 Application Research of Computers
基金 国家自然科学基金资助项目(61074153)
关键词 前馈神经网络 BP网络 粒子群优化 混沌映射 feedforward neural networks back-propagation neural networks particle swarm optimization chaos map
  • 相关文献

参考文献16

  • 1HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators [ J ]. Neural Networks, 1989,2 (5) :359-366.
  • 2KENNEDY J, EBERHART R C. Particle swarm optimization[ C ]// Proc of IEEE International Conference on Neural Networks. Pisca- taway : IEEE Press, 1995 : 1942-1948.
  • 3SHI Yu-hui, EBERHART R C. Empirical study of particle swarm opti- mization[ C]//Proc of IEEE Congress on Evolutionary Computation. Washington DC : IEEE Press, 1999 : 1945-1950.
  • 4Van Den BERGH F,ENGELBRECHT A P. A new locally convergent particle swarm optimizer[ C ]//Proc of IEEE International Conference on Systems, Man and Cybernetics. [S. l. ] : IEEE Press,2002.
  • 5Van Den BERGH F, ENGELBRECHT A P. A cooperative approach to particle swarm optimization[ J]. IEEE Trans on Evolutionary Com- putation ,2004,8(3 ) :225-239.
  • 6HO S L, YANG S, NI G, et el. A particle swarm optimization method with enhanced global search ability for design optimizations of electro- magnetic devices [ J ]. IEEE Trans on Magnetics, 2006,42 (4) : 1107-1110.
  • 7XIE X, ZANG W, YANG Z. Dissipative swarm optimization [ C ]//Proc of IEEE Congress on Evolutionary Computation. [S. l. ] : IEEE Press, 2002 : 1456-1461.
  • 8LIU B, WANG L, JIN H Y. Improved particle swarm optimization com- bined with chaos [ J ]. Chaos, Solitons 8, Fractals, 2005,25 (5) : 1261-1271.
  • 9吕振肃,侯志荣.自适应变异的粒子群优化算法[J].电子学报,2004,32(3):416-420. 被引量:451
  • 10MUKHOPADHYAY S, BANERJEE S. Global optimization of an opti- cal chaotic system by chaotic multi swarm particle swarm optimization [J]. Expert Systems with Applications,2012,39 (1) :917-924.

二级参考文献43

共引文献612

同被引文献21

引证文献2

二级引证文献10

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