J4

• 计算机科学 • 上一篇    下一篇

Hopfield神经网络在扰动情况下的鲁棒性

李佰成1, 李德昌2, 廉诚雪3, 陈殿友4   

  1. 1. 吉林大学 软件学院, 长春 130012; 2. 吉林大学 计算机科学与技术学院, 长春 130012; 3. 上海交通大学 应用数学系, 上海 200030; 4. 吉林大学 数学学院, 长春 130012
  • 收稿日期:2006-05-31 修回日期:1900-01-01 出版日期:2006-08-26 发布日期:2006-11-26
  • 通讯作者: 李德昌

Robustness of Hopfield Neural Networks in Discrete Perturbation

LI Baicheng1, LI Dechang2, LIAN Cheng xue3, CHEN Dianyou4   

  1. 1. College of Software, Jilin University, Changchun 130012, China; 2. College of Computer Science and Technology, Jilin University, Changchun 130012, China; 3. Department of Application Mathematics, Shanghai Jiaotong University, Shanghai 200030, China;4. College of Mathematics, Jilin University, Changchun 130012, China
  • Received:2006-05-31 Revised:1900-01-01 Online:2006-08-26 Published:2006-11-26
  • Contact: LI Dechang

摘要: Hopfield神经网络在工程领域中应用广泛, 但在具体的实现过程中往往存在着扰动和时滞, 这些因素的存在影响了神经网络的动态性能, 并有可能导致网络失稳. 通过建立模型, 讨论了时滞递归神经网络的鲁棒性, 给出了有效的判定条件, 推广了有关文献中的结果.

关键词: Hopfield神经网络, 鲁棒性, 故障模型, 时滞网络

Abstract: Hopfield neural networks are widely applied in picture identification and engineering field, but there are parameter perturbations and time delay in the neural network when it is implemented with the hardware. T hese factors will badly influence the dynamic performance of the neural network and even cause instability of the network. This paper discusses the robustness of ne ural networks with time delay by building a model. And the fairly general and easily verifiable criterion is presented.

Key words: Hopfield neural networks, robustness, fault model, time delayed networks

中图分类号: 

  • TP13