ROBUSTNESS AND INFORMATION CAPACITY OF LEARNING RULES FOR NEURAL NETWORK MODELS

被引:0
|
作者
SCHNELLE, T
ENGEL, A
机构
[1] Humboldt University, Department of Physics 04, O1040 Berlin
关键词
D O I
10.1016/0375-9601(91)90128-U
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Investigating different learning rules concerning their robustness against dilution and static noise we find a clear complementary relationship between robustness and high storage capacity. For models based on the Hebbian rule it is shown that the information capacity becomes maximal if the synapses are restricted to the values (0, +/- 1 ) only.
引用
收藏
页码:69 / 75
页数:7
相关论文
共 50 条
  • [1] Information capacity and robustness of stochastic neuron models
    Schneidman, E
    Segev, I
    Tishby, N
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 12, 2000, 12 : 178 - 184
  • [2] Information capacity of a hierarchical neural network
    Renato, Carreta Dominguez, David
    [J]. Physical Review E. Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics, 1998, 58 (04):
  • [3] Information capacity of a hierarchical neural network
    Dominguez, DRC
    [J]. PHYSICAL REVIEW E, 1998, 58 (04): : 4811 - 4815
  • [4] A Learning Convolutional Neural Network Approach for Network Robustness Prediction
    Lou, Yang
    Wu, Ruizi
    Li, Junli
    Wang, Lin
    Li, Xiang
    Chen, Guanrong
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (07) : 4531 - 4544
  • [5] Predicted Robustness as QoS for Deep Neural Network Models
    Yue-Huan Wang
    Ze-Nan Li
    Jing-Wei Xu
    Ping Yu
    Taolue Chen
    Xiao-Xing Ma
    [J]. Journal of Computer Science and Technology, 2020, 35 : 999 - 1015
  • [6] Predicted Robustness as QoS for Deep Neural Network Models
    Wang, Yue-Huan
    Li, Ze-Nan
    Xu, Jing-Wei
    Yu, Ping
    Chen, Taolue
    Ma, Xiao-Xing
    [J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2020, 35 (05) : 999 - 1015
  • [7] ON THE INFORMATION-STORAGE CAPACITY OF LOCAL LEARNING RULES
    PALM, G
    [J]. NEURAL COMPUTATION, 1992, 4 (05) : 703 - 711
  • [8] GCRL: a graph neural network framework for network connectivity robustness learning
    Zhang, Yu
    Chen, Haowei
    Chen, Qiyu
    Ding, Jie
    Li, Xiang
    [J]. NEW JOURNAL OF PHYSICS, 2024, 26 (09):
  • [9] Controlling information capacity of binary neural network
    Ignatov, Dmitry
    Ignatov, Andrey
    [J]. PATTERN RECOGNITION LETTERS, 2020, 138 : 276 - 281
  • [10] On The Robustness of a Neural Network
    El Mhamdi, El Mahdi
    Guerraoui, Rachid
    Rouault, Sebastien
    [J]. 2017 IEEE 36TH INTERNATIONAL SYMPOSIUM ON RELIABLE DISTRIBUTED SYSTEMS (SRDS), 2017, : 84 - 93