GENETIC DESIGN OF SPARSE FEEDFORWARD NEURAL NETWORKS

被引：8
|
作者：
SAHA, S
CHRISTENSEN, JP
机构：
[1] Department of Electrical and Computer Engineering, Louisiana State University, Baton Rouge
来源：
INFORMATION SCIENCES | 1994年 / 79卷 / 3-4期
关键词：
D O I：
10.1016/0020-0255(94)90119-8
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A novel scheme has been proposed to design neural networks. The method attempts to find an architecture and the corresponding weights and thresholds of the neural network simultaneously. Various rules have been formulated to encode the architecture and network parameters into a string of bits, and the genetic algorithm has been used to find a beneficial (if not optimal) string. The proposed scheme has been tested on the XOR problem. The neural networks which have been designed by this approach include interesting examples of shortcut or bypass, and sparse neural networks.
引用
收藏
页码：191 / 200
页数：10
相关论文
共 50 条
  • [1] Learning and structural design of feedforward neural networks by employing genetic algorithms
    Bohari, AR
    Mizuno, N
    [J]. SICE '96 - PROCEEDINGS OF THE 35TH SICE ANNUAL CONFERENCE: INTERNATIONAL SESSION PAPERS, 1996, : 1377 - 1382
  • [2] Training and structure design of feedforward neural networks by employing genetic algorithms
    Bohari, AR
    Mizuno, N
    [J]. 1998 JAPAN-U.S.A. SYMPOSIUM ON FLEXIBLE AUTOMATION - PROCEEDINGS, VOLS I AND II, 1998, : 769 - 776
  • [3] Training feedforward neural networks using neural networks and genetic algorithms
    Tellez, P
    Tang, Y
    [J]. INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATIONS AND CONTROL TECHNOLOGIES, VOL 1, PROCEEDINGS, 2004, : 308 - 311
  • [4] Orthogonal Super Greedy Learning for Sparse Feedforward Neural Networks
    Xu, Lin
    Cao, Xiangyong
    Yao, Jing
    Yan, Zheng
    [J]. IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2022, 9 (01): : 161 - 170
  • [5] ON THE DESIGN OF FEEDFORWARD NEURAL NETWORKS FOR BINARY MAPPINGS
    TAN, SH
    VANDEWALLE, J
    [J]. NEUROCOMPUTING, 1994, 6 (5-6) : 565 - 582
  • [6] Feedforward neural networks design by evolutionary programming
    Li, ZG
    Hu, SR
    Lu, HY
    [J]. CRITICAL TECHNOLOGY: PROCEEDINGS OF THE THIRD WORLD CONGRESS ON EXPERT SYSTEMS, VOLS I AND II, 1996, : 1247 - 1254
  • [7] A Hybrid Genetic Algorithm for Designing Feedforward Neural Networks
    Xu, Jinhua
    Lu, Yue
    [J]. 2008 3RD INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEM AND KNOWLEDGE ENGINEERING, VOLS 1 AND 2, 2008, : 549 - 554
  • [8] Evolutional design and training algorithm for feedforward neural networks
    Takahashi, H
    Nakajima, M
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1999, E82D (10) : 1384 - 1392
  • [9] Heterogeneous double populations based hybrid genetic algorithm design for training feedforward neural networks
    Zhang, Li Feng
    He, Rong
    Yan, Meng Ling
    [J]. 2012 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2012,
  • [10] A NOVEL DESIGN METHOD FOR MULTILAYER FEEDFORWARD NEURAL NETWORKS
    LEE, J
    [J]. NEURAL COMPUTATION, 1994, 6 (05) : 885 - 901
12345