期刊文献+

基于复数权神经元的多值整形器稳健设计

Robust Design of Multiple Reshaper Based on Neuron with Complex Valued Weights
在线阅读 下载PDF
导出
摘要 复数权神经元是由于引入多阈值逻辑而使得权值为复数的神经元,被认为具有更强的性能。该文根据该神经元数学模型,结合POST代数系统中多值逻辑取值及运算的概念,实现了基于单个复数权神经元的多值整形运算,设计的多值逻辑整形运算具有稳健性能,所得结果表明用复数权神经元实现多值逻辑的有效性和可行性,说明了其强大的信息处理能力。 Neurons with complex-valued weights have stronger capability because of its multi-valued threshold logic.In the paper,a multi-valued reshaper is implemented according to both the neuron's mathematics model and POST algebra system and its operation.More over the designed reshaper has robustness feature.So the result is believed that the validity and possibility with such kind of neurons for multi-valued logic as well as its strong capability for information processing.
作者 吕伟锋 林弥
出处 《杭州电子科技大学学报(自然科学版)》 2008年第1期20-23,共4页 Journal of Hangzhou Dianzi University:Natural Sciences
基金 杭州电子科技大学科学研究基金资助项目(KYF051507001)
关键词 复数权值 多值神经元 多值逻辑 稳健神经元 complex-valued weights multi-valued neurons multi-valued logic robust neurons
  • 相关文献

参考文献11

  • 1[1]Aizenberg N,Aizenberg I,Krivosheev G.Multi-valued and universal binary neurons:mathematical model,learning,networks,application to image processing and pattern recognition[C].Proc.of the 13rd International conference on Pattern Recognition,IEEE Computer Soc.Press,1996:185-189.
  • 2[2]Jankowski S,Lozowski A,Zurada M.Complex-Valued Multi-state Neural Associative Memory[J].IEEE Trans.on Neural Networks,1996,(7):1491-1496.
  • 3[3]Aizenberg I,Aizenberg N,Butakov C.Farberov E.Image recognition on the neural network based on multi-valued neurons[C].Proceedings of the 15th International Conference on Pattern Recognition,IEEE Computer Society Press,2000,2:989-992.
  • 4[4]Su Lee Goh,Danilo P Mandic.Nonlinear Adaptive Prediction of Complex-Valued Signals by Complex-Valued PRNN[J].IEEE Trans on signal processing,2005,53(5):1827-1836.
  • 5[5]Muezzinoglu M K,Guzelis C,Zurada J.M.A new design method for the complex-valued multistate Hopfield associative memory[J].IEEE Transaction on Neural Networks,2003,14(4):891-899.
  • 6[6]Gray D L,Miched A.A training algorithm for binary feedforward neural networks[J].IEEE Transaction on Neural Networks,1992,3(2):176-194.
  • 7[7]Hundiwal A K.An improved algorithm for learning representations in Boolean neural networks[J].IEEE Transaction on Circuits and Systems,Proceedings of The 36th Midwest Symposium on,1993:592-595.
  • 8[8]Zhang Junying,Xu Jin,Bao Zheng.Analysis and design of most tolerant logic neural networks[C].Proceedings of the 3rd International conference on signal proceeding,1996:1425-1428.
  • 9张军英,保铮.稳健二进神经网络的几何训练[J].控制与决策,2001,16(6):864-868. 被引量:1
  • 10吕伟锋,王柏祥,章专.数字逻辑的稳健神经网络实现[J].浙江大学学报(理学版),2003,30(6):642-645. 被引量:6

二级参考文献11

  • 1王继成,吕维雪.基于神经网络的逻辑计算[J].计算机工程与设计,1993,14(2):29-35. 被引量:2
  • 2张军英.二进前向网络的分类超平面理论[M].西安:西安电子科技大学,1998..
  • 3HUNDIWAL A K. An improved algorithm for learning representations in Boolean neural networks [J].IEEE Transaction on Circuits and Systems, Proceedings of The 36th Midwest Symposium on, 1993, 16-18:592-595.
  • 4GRAY D L, MICHED A N. A training algorithm for binary feedforward neural networks[J]. IEEE Transaction on Neural Networks, 1992, 3 (2) : 176- 194.
  • 5JOHNSON M L. Perceptron- how this neural network model lets you evaluate Boolean functions [J].IEEE Potentials,1993, 12(3): 17-18.
  • 6张军英,学位论文,1998年
  • 7Jung H Kim,IEEE Trans Neural Networks,1995年,6卷,1期,237页
  • 8王国胤,施鸿宝.TMLNNs:三值/多值逻辑神经元网络[J].计算机学报,1997,20(7):630-639. 被引量:5
  • 9许力,诸静,蒋静坪.一种基于对称三值逻辑的多值学习网络[J].计算机学报,1998,21(6):553-559. 被引量:1
  • 10马晓敏,胡子萍.数字逻辑的神经网络设计[J].电路与系统学报,1998,3(3):51-58. 被引量:10

共引文献7

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