A new strategy for adaptively constructing multilayer feedforward neural networks

被引：55
|
作者：
Ma, L [1 ]
Khorasani, K [1 ]
机构：
[1] Concordia Univ, Dept Elect & Comp Engn, Montreal, PQ H3G 1M8, Canada
来源：
NEUROCOMPUTING | 2003年 / 51卷
关键词：
constructive networks; multilayer feedforward neural networks; regression and function approximation;
D O I：
10.1016/S0925-2312(02)00597-0
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper a new strategy for adaptively and autonomously constructing a multi-hidden-layer feedforward neural network (FNN) is introduced. The proposed scheme belongs to a class of structure level adaptation algorithms that adds both new hidden units and new hidden layers one at a time when it is determined to be needed. Using this strategy, a FNN may be constructed having as many hidden layers and hidden units as required by the complexity of the problem being considered. Simulation results applied to regression problems are included to demonstrate the performance capabilities of the proposed scheme. (C) 2002 Elsevier Science B.V. All rights reserved.
引用
收藏
页码：361 / 385
页数：25
相关论文
共 50 条
  • [41] On Partial Groupoids Associated with the Composition of Multilayer Feedforward Neural Networks
    Litavrin, Andrey, V
    Moiseenkova, Tatyana, V
    BULLETIN OF IRKUTSK STATE UNIVERSITY-SERIES MATHEMATICS, 2024, 50 : 101 - 115
  • [42] A new strategy for constructing higher order neural networks with multiplication units
    Li, D
    Hirasawa, K
    Hu, JL
    SICE 2003 ANNUAL CONFERENCE, VOLS 1-3, 2003, : 2342 - 2347
  • [43] Two-dimensional learning strategy for multilayer feedforward neural network
    Chow, TWS
    Fang, Y
    NEUROCOMPUTING, 2000, 34 (34) : 195 - 206
  • [44] Adaptively Transferring Deep Neural Networks with a Hybrid Evolution Strategy
    Zhang, Xiaoling
    Gong, Yue-Jiao
    Xiao, Xiaolin
    2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 1068 - 1074
  • [45] A modified approach for constructing the self-organized layer in a multilayer feedforward neural network
    Li, RY
    Lebby, GL
    Si, HX
    INFORMATION SCIENCES, 1997, 98 (1-4) : 69 - 81
  • [46] Classification of normal and abnormal electrogastrograms using multilayer feedforward neural networks
    Lin, Z.
    Maris, J.
    Hermans, L.
    Vandewalle, J.
    Chen, J.D.Z.
    Medical and Biological Engineering and Computing, 1997, 35 (03): : 199 - 206
  • [47] MULTILAYER FEEDFORWARD NEURAL NETWORKS WITH SINGLE POWERS-OF-2 WEIGHTS
    TANG, CZ
    KWAN, HK
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1993, 41 (08) : 2724 - 2727
  • [48] Classification of normal and abnormal electrogastrograms using multilayer feedforward neural networks
    Z. Lin
    J. Maris
    L. Hermans
    J. Vandewalle
    J. D. Z. Chen
    Medical and Biological Engineering and Computing, 1997, 35 : 199 - 206
  • [49] The quantization effects of different probability distribution on multilayer feedforward neural networks
    Jiang, MH
    Gielen, G
    Deng, BX
    Tang, XF
    Ruan, QQ
    Yuan, BZ
    2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 1175 - 1178
  • [50] Classification of normal and abnormal electrogastrograms using multilayer feedforward neural networks
    Lin, Z
    Maris, J
    Hermans, L
    Vandewalle, J
    Chen, JDZ
    MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 1997, 35 (03) : 199 - 206
12345