DYNAMICS OF LEARNING AND GENERALIZATION IN PERCEPTRONS WITH CONSTRAINTS

被引：2
|
作者：
HORNER, H
机构：
[1] Institut für Theorestische Physik, Universität Heidelberg, D-6900 Heidelberg
来源：
PHYSICA A | 1993年 / 200卷 / 1-4期
关键词：
D O I：
10.1016/0378-4371(93)90560-Q
中图分类号：
O4 [物理学];
学科分类号：
0702 ;
摘要：
Depending on the kind of constraints imposed on the weights of a perceptron, learning can be a combinatorially hard problem. As an example of this type, I discuss a perceptron with binary weights comparing results obtained from replica theory, dynamic mean field theory and simulated annealing. Contrary to the replica calculation, dynamics yields information about the performance of a polynomial algorithm in a situation where the best solution cannot be found in polynomial time. I also discuss improved learning algorithms and results for finite size perceptrons.
引用
收藏
页码：552 / 562
页数：11
相关论文
共 50 条
  • [21] A hybrid learning algorithm for multilayer perceptrons to improve generalization under sparse training data conditions
    Tonomura, M
    Nakayama, K
    IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 967 - 972
  • [22] Learning sparse perceptrons
    Jackson, JC
    Craven, MW
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 8: PROCEEDINGS OF THE 1995 CONFERENCE, 1996, 8 : 654 - 660
  • [23] Theoretical and numerical analysis of learning dynamics near singularity in multilayer perceptrons
    Guo, Weili
    Wei, Haikun
    Zhao, Junsheng
    Zhang, Kanjian
    NEUROCOMPUTING, 2015, 151 : 390 - 400
  • [24] Learning by a population of perceptrons
    Kang, K
    Oh, JH
    Kwon, C
    PHYSICAL REVIEW E, 1997, 55 (03): : 3257 - 3261
  • [25] On learning a function of perceptrons
    Anthony, M
    2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 967 - 972
  • [26] Generalization of finite size Boolean perceptrons with genetic algorithms
    Barbato, D. M. L.
    De Groote, J. J.
    NEUROCOMPUTING, 2008, 71 (16-18) : 3650 - 3655
  • [27] Learning dynamics of simple perceptrons with non-extensive cost functions
    Cannas, SA
    Stariolo, D
    Tamarit, FA
    NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1996, 7 (01) : 141 - 149
  • [28] WEIGHT LIMITING, WEIGHT QUANTIZATION AND GENERALIZATION IN MULTILAYER PERCEPTRONS
    WOODLAND, PC
    FIRST IEE INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS, 1989, : 297 - 300
  • [29] STATISTICAL-MECHANICS OF GENERALIZATION - NEW RESULTS FOR PERCEPTRONS
    KINZEL, W
    PHYSICA A, 1993, 200 (1-4): : 613 - 618
  • [30] DYNAMICS OF LEARNING AND GENERALIZATION IN A BINARY PERCEPTRON MODEL
    HORNER, H
    ZEITSCHRIFT FUR PHYSIK B-CONDENSED MATTER, 1992, 87 (03): : 371 - 376
12345