USE OF SOME SENSITIVITY CRITERIA FOR CHOOSING NETWORKS WITH GOOD GENERALIZATION ABILITY

被引：204
|
作者：
DIMOPOULOS, Y
BOURRET, P
LEK, S
机构：
[1] UNIV TOULOUSE 3,UMR 9964,F-31062 TOULOUSE,FRANCE
[2] CERT,ONERA,DEPT ETUD & RECH INFORMAT,F-31055 TOULOUSE,FRANCE
来源：
NEURAL PROCESSING LETTERS | 1995年 / 2卷 / 06期
关键词：
D O I：
10.1007/BF02309007
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In most applications of the multilayer perceptron (MLP) the main objective is to maximize the generalization ability of the network. We show that this ability is related to the sensitivity of the output of the MLP to small input changes. Several criteria have been proposed for the evaluation of the sensitivity. We propose a new index and present a way for improving these sensitivity criteria. Some numerical experiments allow a first comparison of the efficiencies of these criteria.
引用
收藏
页码：1 / 4
页数：4
相关论文
共 50 条
  • [1] On the generalization ability of recurrent networks
    Hammer, B
    ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS, 2001, 2130 : 731 - 736
  • [2] On the Generalization Ability of GRLVQ Networks
    Barbara Hammer
    Marc Strickert
    Thomas Villmann
    Neural Processing Letters, 2005, 21 : 109 - 120
  • [3] Generalization ability of folding networks
    Hammer, B
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2001, 13 (02) : 196 - 206
  • [4] On the generalization ability of GRLVQ networks
    Hammer, B
    Strickert, M
    Villmann, T
    NEURAL PROCESSING LETTERS, 2005, 21 (02) : 109 - 120
  • [5] GENERALIZATION ABILITY OF MOS PREDICTION NETWORKS
    Cooper, Erica
    Huang, Wen-Chin
    Toda, Tomoki
    Yamagishi, Junichi
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 8442 - 8446
  • [6] GENERALIZATION ABILITY OF OPTIMAL CLUSTER SEPARATION NETWORKS
    WENDEMUTH, A
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1994, 27 (07): : 2325 - 2333
  • [7] Empirical estimation of generalization ability of neural networks
    Sarkar, D
    APPLICATIONS AND SCIENCE OF ARTIFICIAL NEURAL NETWORKS II, 1996, 2760 : 54 - 60
  • [8] ON THE ABILITY OF NEURAL NETWORKS TO PERFORM GENERALIZATION BY INDUCTION
    ANSHELEVICH, VV
    AMIRIKIAN, BR
    LUKASHIN, AV
    FRANKKAMENETSKII, MD
    BIOLOGICAL CYBERNETICS, 1989, 61 (02) : 125 - 128
  • [9] Empirical estimation of generalization ability of neural networks
    Sarkar, D.
    Neural Network World, 2001, 11 (01) : 3 - 15
  • [10] NOTE - SOME CRITERIA FOR CHOOSING BETWEEN EXPLANATIONS IN PSYCHOLOGY
    PAXTON, R
    BULLETIN OF THE BRITISH PSYCHOLOGICAL SOCIETY, 1976, 29 (DEC): : 396 - 399
12345