期刊文献+

遗传算法设计神经网络的一种新方法

A novel approach for optimizing neural networks with genetic algorithms
下载PDF
导出
摘要 提出了一种基于平均风险误差准则的遗传算法优化设计前向神经网络的方法,遗传算法的适应度函数并不采用基于传统的最小均方误差准则,而是由最小平均风险误差准则所决定,这种方法在计算神经网络输出与期望输出之间误差的同时,还要考虑神经网络对每一类训练样本产生的这种误差所引起的风险损失.这种方法优化得到的神经网络不但可以准确地再现训练样本集合的期望输出,对训练样本集合外样本的预测能力也有明显的提高. A novel approach for optimizing feed forward neural networks is proposed in this paper, the genetic algorithms is not based on the traditional criterion of minimized square error, however its fitness function is determined by the average risk. The method considered not only the errors between the network's outputs and the desired outputs, but also the risk caused by these errors, because the errors for different types of samples in training set may present different risks. The neural networks optimized by the proposed approach shows good performance on the samples both inside and outside training set.
出处 《厦门大学学报(自然科学版)》 CAS CSCD 北大核心 2001年第z1期54-57,共4页 Journal of Xiamen University:Natural Science
基金 江西省跨世纪学科带头人培养计划项目(第3批) 江西省自然科学基金资助项目(9911013)
关键词 遗传算法:神经网络 优化设计 风险误差 genetic algorithm neural networks optimization risk
  • 相关文献

参考文献6

  • 1[1]Baeck T U Hammel, H-P Schwefel. Evolutionary computation: Comments on history and currentstate[J]. IEEE Transactions on Evolutionary Computation, 1997,1(1): 3-17.
  • 2[2]Yao X. A reviews of evolutionary artificial neural networks[J]. International Journal of Intelligent Systems,8, 1993,8:539-567.
  • 3[3]Bruce A W, Timothy D C. Evolving space-filling curves to distribute radial basis functions over an inputspace[J]. IEEE Transactions on Neural Networks, 1994,5:15-23.
  • 4[4]Bornholdt S, Graudenz D. General asymmetric neural network and structure design by geneticalgorithms[J]. Neural Networks, 1992,5:327-334.
  • 5[5]Vittorio M. Genetic evolution of the topology and weight distribution of neural networks[J].IEEETransactions on Neural Networks, 1994,5:39-53.
  • 6黎明,严超华,刘高航.基于掌纹图象分析的身份识别系统[J].中国图象图形学报(A辑),2000,5(2):134-137. 被引量:17

二级参考文献15

  • 15,Cardot H, Revenu M et al. An artificial neural networks architecture for handwritten signature authentication. In:Proc SPIE, 1993, 1965:633~644.
  • 26,Peckham J. I'd know that voice anywhere(security). Systems International, 1989, 17(9):49~50.
  • 37,Matsumoto K. Palm-recognition systems:An ideal means of restricting access to high-security areas. Mitsubishi Electric Advance, 1985, 31:31~32.
  • 48,Shiono M, Ishikawa H et al. An experiment on personal identification for gate security using hand shape and palm-print. Transactions of the Institute of Electronics, Information and Communication Engineering D-II, 1991, J74D-II(6):688~697.
  • 59,Kung S Y, Lin S H et al. Neural Networks for Signal Processing. Cambridge, MA, USA, 1995:323~332.
  • 610,LI Ming, Paul S W. Pyramid edge detection for color image. Optical Engineering, 1997, 36(5):1425~1430.
  • 711,Pual S W, LI Ming. Pyramid edge detection based on stack filter. Pattern Recognition Letters, 1997, 18(3):239~248.
  • 812,Paul S W, LI Ming. Pyrmid adaptive dynamic Hough transform to detect edges with arbitrary shapes. Optical Engineering, 1997, 36(5):1431~1437.
  • 913,Roz L. Palmistry: How to Chart the Lines of Your Destiny. Simon & Schuster Inc, New York, 1993.
  • 1014,Carpenter G A, Grossberg S. A massively parallel architecture for a self organizing neural pattern recognition machine. Computer Vision, Graphics, and Image Processing. 1987, 37:54~115.

共引文献16

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