Hidden-layer redundancy method of RBF neural networks

被引：0
|
作者：
Xu, Li-Qin [1 ]
Hu, Dong-Cheng [1 ]
机构：
[1] Dept. of Automat., Tsinghua Univ., Beijing 100084, China
来源：
Kongzhi yu Juece/Control and Decision | 2001年 / 16卷 / 05期
关键词：
Algorithms - Architecture - Computer simulation - Fault tolerant computer systems - Fault tree analysis - Redundancy - Theorem proving;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
A hidden-layer neuron redundancy architecture of RBF network is presented. Performance of the network are analyzed under both single-fault and universal faults. The performance of the network under faults can be improved significantly with this redundancy architecture. Finally, a practical method of redundancy of hidden-layer neurons to gain fault tolerance is presented. Simulation results show the validity of the method.
引用
收藏
页码：591 / 594
相关论文
共 50 条
  • [1] SENSITIVITY ANALYSIS OF SINGLE HIDDEN-LAYER NEURAL NETWORKS WITH THRESHOLD FUNCTIONS
    OH, SH
    LEE, YJ
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (04): : 1005 - 1007
  • [2] Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition
    Li, Ruizhi
    Mallidi, Sri Harish
    Burget, Lukas
    Plchot, Oldrich
    Dehak, Najim
    17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 3265 - 3269
  • [3] Design of neural networks with the hidden-layer control part and memory part
    Lim, CW
    Kim, JM
    Han, SJ
    Park, J
    PROCEEDINGS OF THE 1996 IEEE IECON - 22ND INTERNATIONAL CONFERENCE ON INDUSTRIAL ELECTRONICS, CONTROL, AND INSTRUMENTATION, VOLS 1-3, 1996, : 893 - 897
  • [4] Sensitivity analysis of single hidden-layer neural networks with threshold functions
    Electronics and Telecommunications, Research Inst, Daejeon, Korea, Republic of
    IEEE Trans Neural Networks, 4 (1005-1007):
  • [5] Hidden-layer size reducing for multilayer neural networks using the orthogonal least-squares method
    Yang, ZJ
    SICE '97 - PROCEEDINGS OF THE 36TH SICE ANNUAL CONFERENCE, INTERNATIONAL SESSION PAPERS, 1997, : 1089 - 1092
  • [6] DNA microarray classification with compact single hidden-layer feedforward neural networks
    Huynh, Hieu Trung
    Kim, Jung-Ja
    Won, Yonggwan
    PROCEEDINGS OF THE FRONTIERS IN THE CONVERGENCE OF BIOSCIENCE AND INFORMATION TECHNOLOGIES, 2007, : 193 - +
  • [7] Analysis and application of redundancy on hidden-layer neurons under universal faults
    Xu, Li-Qin
    Hu, Dong-Cheng
    Gao, Jian-Bo
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2001, 29 (05): : 682 - 685
  • [8] Evolutionary single hidden-layer feed forward networks
    Safi, Youssef
    Bouroumi, Abdelaziz
    International Journal of Innovative Computing and Applications, 2014, 6 (02) : 73 - 86
  • [9] Comparing support vector machines and feedforward neural networks with similar hidden-layer weights
    Romero, Enrique
    Toppo, Daniel
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (03): : 959 - 963
  • [10] Hidden-layer neuron redundancy - Analysis and application in MLP's fault tolerance
    Xu, LQ
    Hu, DC
    Gao, JB
    PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-5, 2000, : 800 - 804
12345