Decision trees can initialize radial-basis function networks

被引：78
|
作者：
Kubat, M [1 ]
机构：
[1] Univ SW Louisiana, Ctr Adv Comp Studies, Lafayette, LA 70504 USA
[2] Southern Univ, Dept Comp Sci, Baton Rouge, LA 70813 USA
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1998年 / 9卷 / 05期
关键词：
decision trees; neural networks; pattern recognition; radial-basis functions;
D O I：
10.1109/72.712154
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Successful implementations of radial-basis function (RBF) networks for classification tasks must deal with architectural issues, the burden of irrelevant attributes, scaling, and some other problems, This paper addresses these issues by initializing RBF networks with decision trees that define relatively pure regions in the instance space; each of these regions then determines one basis function. The resulting network is compact, easy to induce, and has favorable classification accuracy.
引用
收藏
页码：813 / 821
页数：9
相关论文
共 50 条
  • [1] On the Kernel Widths in Radial-Basis Function Networks
    Nabil Benoudjit
    Michel Verleysen
    [J]. Neural Processing Letters, 2003, 18 : 139 - 154
  • [2] On the kernel widths in radial-basis function networks
    Benoudjit, N
    Verleysen, M
    [J]. NEURAL PROCESSING LETTERS, 2003, 18 (02) : 139 - 154
  • [3] Radial-Basis Function Neural Network Synthesis on the Basis of Decision Tree
    Subbotin, Sergey
    [J]. OPTICAL MEMORY AND NEURAL NETWORKS, 2020, 29 (01) : 7 - 18
  • [4] Radial-Basis Function Neural Network Synthesis on the Basis of Decision Tree
    Sergey Subbotin
    [J]. Optical Memory and Neural Networks, 2020, 29 : 7 - 18
  • [5] Radial basis function networks and decision trees in the determination of a classifier
    Miglio, R
    Pillati, M
    [J]. DATA ANALYSIS, CLASSIFICATION, AND RELATED METHODS, 2000, : 211 - 216
  • [6] Relaxed conditions for radial-basis function networks to be universal approximators
    Liao, Y
    Fang, SC
    Nuttle, HLW
    [J]. NEURAL NETWORKS, 2003, 16 (07) : 1019 - 1028
  • [7] Sensitivity of radial-basis networks to single-example decision classes
    Imam, IF
    [J]. ICEEC'04: 2004 INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONIC AND COMPUTER ENGINEERING, PROCEEDINGS, 2004, : 333 - 336
  • [8] Prediction of Medical Examination Results Using Radial-Basis Function Networks
    Jang, Gil-Jin
    Kim, Minho
    Kim, Young-Won
    Choi, Jaehun
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS-ASIA (ICCE-ASIA), 2016,
  • [9] A comment on "Relaxed conditions for radial-basis function networks to be universal approximators"
    Wu, Wei
    Nan, Dong
    Long, Jin-ling
    Ma, Yu-mei
    [J]. NEURAL NETWORKS, 2008, 21 (10) : 1464 - 1465
  • [10] Performance of radial-basis function networks for direction of arrival estimation with antenna arrays
    ElZooghby, AH
    Christodoulou, CG
    Georgiopoulos, M
    [J]. IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 1997, 45 (11) : 1611 - 1617
12345