Some novel real/complex-valued neural network models

被引：2
|
作者：
Garimella, Ramamurthy [1 ]
机构：
[1] Int Inst Informat Technol, Hyderabad, Andhra Pradesh, India
来源：
Computational Intelligence, Theory and Application | 2006年
关键词：
synapse model; continuous time perception; biological neural networks;
D O I：
10.1007/3-540-34783-6_47
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Traditional models of neurons are based on the assumption that a synapse is a lumped element represented by a scalar synaptic weight. But to faithfully model biological neurons, synapse is considered as a linear filter. Thus, a new model of continuous time neuron is discussed. It is described how such model leads to interesting neural networks. Also continuous time, complex-valued neuron is discussed. It is also described, how a synapse can be modeled as an FIR filter. Such a model of neuron leads to practically useful neural networks. A novel, continuous time associative memory is proposed. An approach to resolve the convergence of state of such an associative memory is discussed. Various interesting generalizations of neural networks are described.
引用
收藏
页码：473 / 483
页数：11
相关论文
共 38 条
  • [21] Constrained Quaternion-Variable Convex Optimization: A Quaternion-Valued Recurrent Neural Network Approach
    Liu, Yang
    Zheng, Yanling
    Lu, Jianquan
    Cao, Jinde
    Rutkowski, Leszek
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (03) : 1022 - 1035
  • [22] Probabilistic Neural Network With Complex Exponential Activation Functions in Image Recognition
    Savchenko, Andrey
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (02) : 651 - 660
  • [23] SANTIAGO - A Real-Time Biological Neural Network Environment for Generative Music Creation
    Kerllenevich, Hernan
    Ernesto Riera, Pablo
    Camilo Eguia, Manuel
    APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT II, 2011, 6625 : 344 - 353
  • [24] Some Dynamical Behaviors of Fractional-Order Commutative Quaternion-Valued Neural Networks via Direct Method of Lyapunov
    Xia, Yannan
    Chen, Xiaofeng
    Lin, Dongyuan
    Li, Zhongshan
    IEEE ACCESS, 2021, 9 : 693 - 708
  • [25] Real-Time Phase-Only Nulling Based on Deep Neural Network With Robustness
    Zhao, Zhonghui
    Zhao, Huiling
    Zheng, Mingxuan
    Tang, Junjie
    IEEE ACCESS, 2019, 7 : 142287 - 142294
  • [26] A Novel Memristive Multiscroll Multistable Neural Network With Application to Secure Medical Image Communication
    Zhang, Sen
    Peng, Xuenan
    Wang, Xiaoping
    Chen, Chengjie
    Zeng, Zhigang
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 35 (02) : 1774 - 1786
  • [27] Dynamic Neural Network Models for Time-Varying Problem Solving: A Survey on Model Structures
    Hua, Cheng
    Cao, Xinwei
    Xu, Qian
    Liao, Bolin
    Li, Shuai
    IEEE ACCESS, 2023, 11 : 65991 - 66008
  • [28] Convolutional Neural Network Based on Complex Networks for Brain Tumor Image Classification With a Modified Activation Function
    Huang, Zhiguan
    Du, Xiaohao
    Chen, Liangming
    Li, Yuhe
    Liu, Mei
    Chou, Yao
    Jin, Long
    IEEE ACCESS, 2020, 8 : 89281 - 89290
  • [29] A Novel Bayesian Neural Network Approach for Nuclear Root-Mean-Square Charge Radii
    Zhang, X.
    Liu, X.
    Zheng, H.
    Lin, W.
    Wada, R.
    Han, J.
    Ma, C. W.
    Qiao, C. Y.
    Peng, D.
    Huang, Y.
    Leng, Q.
    Qu, G.
    Ren, P.
    Yang, Z.
    IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2025, 72 (03) : 795 - 806
  • [30] Stability of Delayed Reaction-Diffusion Neural-Network Models With Hybrid Impulses via Vector Lyapunov Function
    Wei, Tengda
    Li, Xiaodi
    Cao, Jinde
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (10) : 7467 - 7478
1234