A structural learning of neural-network classifiers using PCA networks and Species Genetic Algorithms

被引：0
|
作者：
Kim, SW
Shin, SH
Aoki, Y
机构：
[1] Myongji Univ, Dept Comp Engn, Yongin 449728, Kyunggi Do, South Korea
[2] Hokkaido Univ, Grad Sch Engn, Sapporo, Hokkaido 0608628, Japan
来源：
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES | 1998年 / E81A卷 / 06期
关键词：
neural-network architecture; Principal Component Analysis network; Species Genetic Algorithm;
D O I：
暂无
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
We present experimental results for a structural learning method of feed-forward neural-network classifiers using Principal Component Analysis (PCA) network and Species Genetic Algorithm (SGA). PCA network is used as a means for reducing the number of input units. SGA, a modified GA, is employed for selecting the proper number of hidden units and optimizing the connection links. Experimental results show that the proposed method is a useful tool for choosing an appropriate architecture for high dimensions.
引用
收藏
页码：1183 / 1186
页数：4
相关论文
共 50 条
  • [1] USING GENETIC ALGORITHMS FOR AN ARTIFICIAL NEURAL-NETWORK MODEL INVERSION
    DEWEIJER, AP
    LUCASIUS, CB
    BUYDENS, L
    KATEMAN, G
    HEUVEL, HM
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1993, 20 (01) : 45 - 55
  • [2] Evaluation of neural-network classifiers for weed species discrimination
    Burks, TF
    Shearer, SA
    Heath, JR
    Donohue, KD
    [J]. BIOSYSTEMS ENGINEERING, 2005, 91 (03) : 293 - 304
  • [3] Comparing Mechanical Neural-Network Learning Algorithms
    Lee, Ryan H. H.
    Sainaghi, Pietro
    Hopkins, Jonathan B.
    [J]. JOURNAL OF MECHANICAL DESIGN, 2023, 145 (07)
  • [4] Feature selection for neural network classifiers using saliency and genetic algorithms
    DeRouin, E
    Brown, JR
    Denney, G
    [J]. APPLICATIONS AND SCIENCE OF COMPUTATIONAL INTELLIGENCE, 1998, 3390 : 322 - 331
  • [5] ROBUST ESTIMATION OF PRINCIPAL COMPONENTS BY USING NEURAL-NETWORK LEARNING ALGORITHMS
    CICHOCKI, A
    UNBEHAUEN, R
    [J]. ELECTRONICS LETTERS, 1993, 29 (21) : 1869 - 1870
  • [6] Multistage classifiers optimized by neural networks and genetic algorithms
    Benediktsson, JA
    Sveinsson, JR
    Ingimundarson, JI
    Sigurdsson, HS
    Ersoy, OK
    [J]. NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 1997, 30 (03) : 1323 - 1334
  • [7] Neural Networks versus Genetic Algorithms as Medical Classifiers
    Marin, Oscar
    Perez, Irene
    Ruiz, Daniel
    Soriano, Antonio
    Garcia, Joaquin D.
    [J]. FOUNDATIONS ON NATURAL AND ARTIFICIAL COMPUTATION: 4TH INTERNATIONAL WORK-CONFERENCE ON THE INTERPLAY BETWEEN NATURAL AND ARTIFICIAL COMPUTATION, IWINAC 2011, PART I, 2011, 6686 : 393 - 400
  • [8] ON THE GENERALIZATION ABILITY OF NEURAL-NETWORK CLASSIFIERS
    MUSAVI, MT
    CHAN, KH
    HUMMELS, DM
    KALANTRI, K
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1994, 16 (06) : 659 - 663
  • [9] Constructive neural-network learning algorithms for pattern classification
    Parekh, R
    Yang, JH
    Honavar, V
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02): : 436 - 451
  • [10] Improvement of Neural-Network Classifiers Using Fuzzy Floating Centroids
    Liu, Shuangrong
    Wang, Lin
    Yang, Bo
    Zhou, Jin
    Chen, Zhenxiang
    Dong, Huifen
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (03) : 1392 - 1404
12345