期刊文献+

基于复合适应度微粒群算法的神经网络训练 被引量:5

Neural Network Training Based on Compound Fitness Particle Swarm Optimization
下载PDF
导出
摘要 为提高神经网络的泛化能力,针对以均方误差为适应度的PSO算法在训练神经网络时会产生一定的过拟合问题,提出对均方误差和误差分布均匀度进行信息融合,构成复合适应度作为训练指标.实验结果表明,该方法可使网络的泛化能力得到明显的改善. The over fitting arises if the PSO(particle swarm optimization) algorithm whose fitness is mean squared eviation is applied in training neural network. In order to improve generalization capacity of feedforward neural network. The compound fitness based on information merging of mean square deviation and error uniformity is proposed as the training index of PSO. The results show that the approach can improve the generalization capacity of feedforward neural networks remarkably.
出处 《控制与决策》 EI CSCD 北大核心 2005年第8期958-960,共3页 Control and Decision
基金 天津市自然科学基金重点项目(033803311) 天津市高等学校科技发展基金项目(20041705)
关键词 微粒群算法 神经网络 复合适应度 泛化能力 Particle swarm optimization Neural network Compound fitness Generalization ability
  • 相关文献

参考文献9

  • 1张德贤.基于输出误差与偏导数误差信息融合的神经网络训练[J].计算机工程与应用,2002,38(24):55-57. 被引量:2
  • 2Coello C A,Pulido G T,Lechuga M S. Handling Multiple Objectives with Particle Swarm Optimization[J]. IEEE Trans on Evolutionary Computation,2004,8(3):256-279.
  • 3Naka S, Genji T, Yura T, et al. A Hybrid Particle Swarm Optimization for Distribution State Estimation[J]. IEEE Trans on Power Systems,2003,18(1):60-68.
  • 4Kassabalidis I N, Sharkawi M A, Marks R J, et al. Dynamic Security Border Identification Using Enhanced Particle Swarm Optimization[J]. IEEE Trans on Power Systems,2002,17(3):723-729.
  • 5Parsopoulos K E, Vrahatis M N.On the Computation of All Global Minimizers through Particle Swarm Optimization[J]. IEEE Trans on Evolutionary Computation,2004,8(3):211-224.
  • 6Wachowiak M P,Smolikova R,Zheng Y, et al. An Approach to Multimodal Biomedical Image Regis-tration Utilizing Particle Swarm Optimization[J]. IEEE Trans on Evolutionary Computation,2004,8(3):289-301.
  • 7Boeringer D W, Werner D H. Particle Swarm Optimization Versus Genetic Algorithms for Phased Array Synthesis[J]. IEEE Trans on Antennas and Propagation,2004,52(3):771-779.
  • 8Vanden Bergh F, Engelbrecht A P.A Cooperative Approach to Particle Swarm Optimization[J]. IEEE Trans on Evolutionary Computation,2004,8(3):225-239.
  • 9Robinson J, Rahmat Samii Y. Particle Swarm Optimization in Electromagnetics[J]. IEEE Trans on Antennas and Propagation,2004,52(2):397-407.

二级参考文献9

  • 1S V Kamarthi,S Pittner. Accelerating neural network training using weight extrapolation[J].Neural Networks, 1999; 12(12): 1285~1299
  • 2Charalambous C. Conjugate gradient algorithm for efficient training of artificial neural network[J]IEEE Proceedings-G, 1992; 139(3) :301~310
  • 3Scott Weaver,Leemon Baird,Marios Polycarpou.Using localizing learning to improve supervised learning algorithms[J].IEEE Transaction on neural networks ,2001; 12(5): 1037~1046
  • 4Chi-Tat,Tommy W S Chow. Adaptive regularization parameter selection method for enhancing generalization capability of neural networks [J].Artificial Intelligence,1999;107(2) :347~356
  • 5G Deco,W Finnoff,H G Zimmermann. Unsupervised mutual information criterion for elimination of overtraining in supervised multilayer networks[J].Neural Computation, 1995; (7) :86~107
  • 6C T Leung,T W S Chow,Y F Yam. A least third-order cumulants objective function. 1997; (9) :91~99
  • 7Hongiun Lu et al.A connectionist approach to data mining[C].In:Proceedings of the 21st VLDB Conference,Zurish,Swizerland,1995:81~106
  • 8Franco Scarselli,Ah Chung Tsoi. Universal approximation using feed forward neural networks:A survey of some existing methods and some new results[J].Neural Networks, 1998; 11 (1): 15~37
  • 9Jie Zhang,A J Morris. A sequential learning approach for single hidden lay neural networks[J].Neural Networks, 1997; 11 (1) :65~80

共引文献1

同被引文献65

引证文献5

二级引证文献12

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