Analysis and Synthesis for a class of complex-valued associative memories

被引：0
|
作者：
Liu, Xiaoyu [1 ]
Fang, Kangling [1 ]
Liu, Bin [1 ]
机构：
[1] Wuhan Univ Sci & Technol, Engn Res Ctr Met Automat & Detecting Technol, Minist Educ, Wuhan 430081, CO, Peoples R China
来源：
2009 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS, VOLS 1-3 | 2009年
关键词：
complex-valued neural network; associative memory; synthesis method; stability analysis; NEURAL NETWORKS;
D O I：
10.1109/AIM.2009.5230016
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper we consider a class of complex-valued Hopfield neural network which is a complex value extension of the real-valued Hopfield type neural network. To apply it to complex- valued associative memory (i.e. to store each desired memory as equilibrium of the network) we design a synthesis method. Neither the orthogonal relations between the set of memory patterns nor the symmetric assumption for the interconnection matrix is needed in the synthesis section. The stability analysis based on Lyapunov function is utilized to guarantee each desired memory is attractive.
引用
收藏
页码：198 / +
页数：2
相关论文
共 50 条
  • [41] Projection rule for complex-valued associative memory with large constant terms
    Kitahara, Michimasa
    Kobayashi, Masaki
    IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2012, 3 (03): : 426 - 435
  • [42] Characteristics of the complex-valued associative memory model having penalty term
    Aoki, H
    Kosugi, Y
    ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 2000, 83 (07): : 62 - 70
  • [43] Chaotic Complex-Valued Multidirectional Associative Memory with Adaptive Scaling Factor
    Chino, Takuya
    Osana, Yuko
    2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2013,
  • [44] Noise Robust Gradient Descent Learning for Complex-Valued Associative Memory
    Kobayashi, Masaki
    Yamada, Hirofumi
    Kitahara, Michimasa
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2011, E94A (08) : 1756 - 1759
  • [45] A new design method for complex-valued multistate Hopfield associative memory
    Müezzinoglu, MK
    Güzelis, C
    Zurada, JM
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 45 - 50
  • [46] A new design method for the complex-valued multistate Hopfield associative memory
    Müezzinoglu, MK
    Güzelis, C
    Zurada, JM
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (04): : 891 - 899
  • [47] Analysis of results in complex-valued intercomparisons
    Rodriguez, M.
    2008 CONFERENCE ON PRECISION ELECTROMAGNETIC MEASUREMENTS DIGEST, 2008, : 218 - 219
  • [48] Sliding Modes in a Class of Complex-Valued Nonlinear Systems
    Doria-Cerezo, Arnau
    Olm, Josep M.
    Biel, Domingo
    Fossas, Enric
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2021, 66 (07) : 3355 - 3362
  • [49] Prediction of Complex-Valued Signals by Using Complex-Valued LMK Algorithm
    Menguc, Engin Cemal
    Acir, Nurettin
    2017 25TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2017,
  • [50] Is a Complex-Valued Stepsize Advantageous in Complex-Valued Gradient Learning Algorithms?
    Zhang, Huisheng
    Mandic, Danilo P.
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 27 (12) : 2730 - 2735
12345