BIASED LEARNING IN BOOLEAN PERCEPTRONS

被引：4
|
作者：
KINOUCHI, O [1 ]
CATICHA, N [1 ]
机构：
[1] UNIV SAO PAULO,BR-05508 SAO PAULO,BRAZIL
来源：
PHYSICA A | 1992年 / 185卷 / 1-4期
关键词：
D O I：
10.1016/0378-4371(92)90482-6
中图分类号：
O4 [物理学];
学科分类号：
0702 ;
摘要：
The generalization ability of Hebbian Boolean perceptrons can be improved by a kind of feedback mechanism in which the student net judges the difficulty of a new example from its previous experience. It is shown that by giving a higher weight to the hard examples both generalization and learning abilities can be increased. Analytical as well as numerical results are presented for both cases where the examples are drawn at random or selected in an intelligent form.
引用
收藏
页码：411 / 416
页数：6
相关论文
共 50 条
  • [1] Generalization of finite size Boolean perceptrons with genetic algorithms
    Barbato, D. M. L.
    De Groote, J. J.
    NEUROCOMPUTING, 2008, 71 (16-18) : 3650 - 3655
  • [2] Dilution in Boolean perceptrons that learn from noisy examples
    Barbato, DML
    Fontanari, JF
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1996, 29 (22): : 7003 - 7012
  • [3] Learning sparse perceptrons
    Jackson, JC
    Craven, MW
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 8: PROCEEDINGS OF THE 1995 CONFERENCE, 1996, 8 : 654 - 660
  • [4] Learning by a population of perceptrons
    Kang, K
    Oh, JH
    Kwon, C
    PHYSICAL REVIEW E, 1997, 55 (03): : 3257 - 3261
  • [5] On learning a function of perceptrons
    Anthony, M
    2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 967 - 972
  • [6] Cryptographic Boolean functions with biased inputs
    Sugata Gangopadhyay
    Aditi Kar Gangopadhyay
    Spyridon Pollatos
    Pantelimon Stănică
    Cryptography and Communications, 2017, 9 : 301 - 314
  • [7] Cryptographic Boolean functions with biased inputs
    Gangopadhyay, Sugata
    Gangopadhyay, Aditi Kar
    Pollatos, Spyridon
    Stanica, Pantelimon
    CRYPTOGRAPHY AND COMMUNICATIONS-DISCRETE-STRUCTURES BOOLEAN FUNCTIONS AND SEQUENCES, 2017, 9 (02): : 301 - 314
  • [8] A multifractal phase-space analysis of perceptrons with biased patterns
    Berg, J
    Engel, A
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1998, 31 (11): : 2509 - 2517
  • [9] LEARNING UNLEARNABLE PROBLEMS WITH PERCEPTRONS
    WATKIN, TLH
    RAU, A
    PHYSICAL REVIEW A, 1992, 45 (06): : 4102 - 4110
  • [10] Efficient learning of linear perceptrons
    Ben-David, S
    Simon, HU
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 13, 2001, 13 : 189 - 195
12345