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
  • [41] Learning from correlated patterns by simple perceptrons
    Shinzato, Takashi
    Kabashima, Yoshiyuki
    JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL, 2009, 42 (01)
  • [42] Convergence of stochastic learning in perceptrons with binary synapses
    Senn, W
    Fusi, S
    PHYSICAL REVIEW E, 2005, 71 (06):
  • [43] LEARNING LINEAR THRESHOLD APPROXIMATIONS USING PERCEPTRONS
    BYLANDER, T
    NEURAL COMPUTATION, 1995, 7 (02) : 370 - 379
  • [44] Statistical mechanical analysis of the dynamics of learning in perceptrons
    C. W. H. MACE
    A. C. C. COOLEN
    Statistics and Computing, 1998, 8 : 55 - 88
  • [45] Fast Learning Network with Parallel Layer Perceptrons
    Guoqiang Li
    Xiaobin Qi
    Bin Chen
    Yunpeng Ma
    Peifeng Niu
    Zhiwang Chen
    Neural Processing Letters, 2018, 47 : 549 - 564
  • [46] On-line learning and generalization in coupled perceptrons
    Bollé, D
    Kozlowski, P
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 2002, 35 (09): : 2093 - 2109
  • [47] Cavity approach to noisy learning in nonlinear perceptrons
    Luo, PX
    Wong, KYM
    PHYSICAL REVIEW E, 2001, 64 (06): : 13 - 061912
  • [48] Subtractive Perceptrons for Learning Images: A Preliminary Report
    Tizhoosh, H. R.
    Kalra, Shivam
    Lifshitz, Shalev
    Babaie, Morteza
    2019 NINTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA), 2019,
  • [49] Learning Boolean formulas
    Kearns, Michael, 1600, ACM, New York, NY, United States (41):
  • [50] Learning Boolean specifications
    Bubeck, U.
    Buening, H. Kleine
    ARTIFICIAL INTELLIGENCE, 2015, 229 : 246 - 257
12345