A LEARNING ALGORITHM FOR RECURRENT RADIAL BASIS FUNCTION NETWORKS

被引：6
|
作者：
MAK, MW [1 ]
机构：
[1] HONG KONG POLYTECH UNIV,DEPT ELECTR ENGN,KOWLOON,HONG KONG
来源：
NEURAL PROCESSING LETTERS | 1995年 / 2卷 / 01期
关键词：
D O I：
10.1007/BF02312380
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper proposes a Recurrent Radial Basis Function network (RRBFN) that can be applied to temporal pattern classifications and predictions. Based on the architecture of the conventional Radial Basis Function networks, the RRBFNs use Gaussian nonlinearity and have feedback paths between every hidden node. These feedback paths enable the networks to learn temporal patterns without an input buffer to hold the recent elements of an input sequence. A gradient descent learning algorithm for the RRBFNs is derived. Two RRBFNs with different number of hidden nodes were tested using a temporal sequence generated by an infinite impulse response filter. The results show that the RRBFNs can approximate the filter more accurate than the Continually Running Fully Recurrent networks trained by the Real-Time Recurrent Learning algorithm.
引用
收藏
页码：27 / 31
页数：5
相关论文
共 50 条
  • [1] An incremental algorithm for learning radial basis function networks
    Blanzieri, E
    Giordana, A
    [J]. FUZZ-IEEE '96 - PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, 1996, : 667 - 673
  • [2] An efficient learning algorithm for function approximation with radial basis function networks
    Oyang, YJ
    Hwang, SC
    [J]. ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 1037 - 1042
  • [3] Fault tolerance in the learning algorithm of radial basis function networks
    Parra, X
    Català, A
    [J]. IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL III, 2000, : 527 - 532
  • [4] A novel learning algorithm for data classification with radial basis function networks
    Oyang, YJ
    Hwang, SC
    Ou, YY
    Chen, CY
    Chen, ZW
    [J]. ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 1021 - 1026
  • [5] Hybrid Learning Algorithm of Radial Basis Function Networks for Reliability Analysis
    Zhang, Dequan
    Zhang, Ning
    Ye, Nan
    Fang, Jianguang
    Han, Xu
    [J]. IEEE TRANSACTIONS ON RELIABILITY, 2021, 70 (03) : 887 - 900
  • [6] PLS algorithm for radial basis function networks
    Wang, Y
    Rong, G
    Wang, SQ
    [J]. PROCEEDINGS OF THE 37TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 1998, : 4748 - 4753
  • [7] RECURRENT LEARNING ALGORITHM FOR TRAINING RADIAL BASIS NEURAL NETWORKS BASED ON APPROXIMATE SETS
    Bodyanskiy, E. V.
    Gorshov, E. V.
    Kolodyazhniy, V. V.
    Pliss, I. P.
    [J]. RADIO ELECTRONICS COMPUTER SCIENCE CONTROL, 2005, 1 : 116 - 122
  • [8] Reinforcement radial basis function neural networks with an adaptive annealing learning algorithm
    Ko, Chia-Nan
    [J]. APPLIED MATHEMATICS AND COMPUTATION, 2013, 221 : 503 - 513
  • [9] ORTHOGONAL LEAST-SQUARES LEARNING ALGORITHM FOR RADIAL BASIS FUNCTION NETWORKS
    CHEN, S
    COWAN, CFN
    GRANT, PM
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (02): : 302 - 309
  • [10] Online learning in radial basis function networks
    Freeman, JAS
    Saad, D
    [J]. NEURAL COMPUTATION, 1997, 9 (07) : 1601 - 1622
12345