MODIFIED HOPFIELD NEURAL NETWORKS FOR RETRIEVING THE OPTIMAL SOLUTION

被引：42
|
作者：
LEE, BW
SHEU, BJ
机构：
[1] UNIV SO CALIF,CTR NEURAL ENGN,LOS ANGELES,CA 90089
[2] UNIV SO CALIF,DEPT ELECT ENGN,INST SIGNAL & IMAGE PROC,LOS ANGELES,CA 90089
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1991年 / 2卷 / 01期
关键词：
D O I：
10.1109/72.80300
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Due to the rugged energy function of the original Hopfield networks, the output is usually one local minimum in the energy function. This paper presents an analysis on the locations of local minima in Hopfield networks and describes a modified network architecture to eliminate such local minima. In particular, another amplifier is introduced at the processor nodes to give correction terms. This modified Hopfield network has been successfully applied to the construction of analog-to-digital converters with optimal solutions. Experimental results on the voltage transfer characteristics of data converters are presented.
引用
收藏
页码：137 / 142
页数：6
相关论文
共 50 条
  • [1] USE OF HOPFIELD NEURAL NETWORKS IN OPTIMAL GUIDANCE
    STECK, JE
    BALAKRISHNAN, SN
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 1994, 30 (01) : 287 - 293
  • [2] Analysis on Hopfield neural networks solution to TSP
    Chen, Ping
    Guo, Jinfeng
    Beijing Youdian Xueyuan Xuebao/Journal of Beijing University of Posts And Telecommunications, 1999, 22 (02): : 58 - 61
  • [3] Robustness analysis of Hopfield and modified Hopfield neural networks in time domain
    Shen, J
    Balakrishnan, SN
    PROCEEDINGS OF THE 37TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 1998, : 1046 - 1051
  • [4] Optimal storage capacity of quantum Hopfield neural networks
    Boedeker, Lukas
    Fiorelli, Eliana
    Miller, Markus
    PHYSICAL REVIEW RESEARCH, 2023, 5 (02):
  • [5] Critical capacity of Hopfield neural networks with optimal storage
    Guo, Donghui
    Chen, Zhenxiang
    Liu, Ruitang
    Wu, Boxi
    Zheng, Liming
    Zheng, Lilong
    Jisuanji Xuebao/Chinese Journal of Computers, 1997, 20 (01): : 77 - 81
  • [6] Existence of Periodic Solution for Hopfield Cellular Neural Networks
    Li, Yanling
    Liu, Anping
    Zhang, Linli
    Hao, Zutao
    PROCEEDINGS OF THE 2009 WRI GLOBAL CONGRESS ON INTELLIGENT SYSTEMS, VOL IV, 2009, : 76 - +
  • [7] Existence and Stability of Periodic Solution for Impulsive Hopfield Neural Networks
    Li, Yanling
    Liu, Anping
    Xiao, Li
    SECOND INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN, VOL 2, PROCEEDINGS, 2009, : 417 - +
  • [8] SOLUTION OF INVERSE PROBLEMS IN ELECTROMAGNETICS USING HOPFIELD NEURAL NETWORKS
    ELSHAFIEY, I
    UDPA, L
    UDPA, SS
    IEEE TRANSACTIONS ON MAGNETICS, 1995, 31 (01) : 852 - 861
  • [9] On Hopfield neural networks
    Feild Jr., William B.
    Navlakha, Jainendra K.
    1600, (01):
  • [10] Modified Augmented Hopfield Neural Network for Optimal Thermal Unit Commitment
    Kamh, Mohamed Z.
    Abdelaziz, Almoataz Y.
    Mekhamer, Said F.
    Badr, Mohamed A. L.
    2009 IEEE POWER & ENERGY SOCIETY GENERAL MEETING, VOLS 1-8, 2009, : 996 - +
12345