Probability limit property for energy function to feed-forward neural networks with noise

被引：0
|
作者：
Jin, C [1 ]
机构：
[1] Hubei Univ, Coll Math & Comp Sci, Wuhun 430062, Peoples R China
来源：
2002 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-4, PROCEEDINGS | 2002年
关键词：
noise; feed-forward neural network; energy function;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, a probability limit property is proposed for the weight vectors W of feed-forward neural network when both the input data and output data contain noise or when only the output data contains noise. By the theory analysis for energy function to feed-forward neural network, this paper points out that a least square energy function isn't a good choice. The result is good enough for future research.
引用
收藏
页码：1 / 3
页数：3
相关论文
共 50 条
  • [1] Feed-forward neural networks
    Bebis, George
    Georgiopoulos, Michael
    IEEE Potentials, 1994, 13 (04): : 27 - 31
  • [2] Empirical prediction limit estimation methods for feed-forward neural networks
    Chinnam, Ratna Babu
    Baruah, Pundarikaksha
    INTERNATIONAL JOURNAL OF GENERAL SYSTEMS, 2007, 36 (02) : 221 - 236
  • [3] Empirical prediction limit estimation methods for feed-forward neural networks
    Chinnam, RB
    Baruah, P
    PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 535 - 540
  • [4] A novel activation function for multilayer feed-forward neural networks
    Aboubakar Nasser Samatin Njikam
    Huan Zhao
    Applied Intelligence, 2016, 45 : 75 - 82
  • [5] A novel activation function for multilayer feed-forward neural networks
    Njikam, Aboubakar Nasser Samatin
    Zhao, Huan
    APPLIED INTELLIGENCE, 2016, 45 (01) : 75 - 82
  • [6] Free Probability for predicting the performance of feed-forward fully connected neural networks
    Chhaibi, Reda
    Daouda, Tariq
    Kahn, Ezechiel
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [7] Free Probability for predicting the performance of feed-forward fully connected neural networks
    Chhaibi, Reda
    Daouda, Tariq
    Kahn, Ezéchiel
    arXiv, 2021,
  • [8] Free Probability for predicting the performance of feed-forward fully connected neural networks
    Chhaibi, Reda
    Daouda, Tariq
    Kahn, Ezéchiel
    Advances in Neural Information Processing Systems, 2022, 35
  • [9] Patterns of synchrony for feed-forward and auto-regulation feed-forward neural networks
    Aguiar, Manuela A. D.
    Dias, Ana Paula S.
    Ferreira, Flora
    CHAOS, 2017, 27 (01)
  • [10] Feed-forward Neural Networks with Trainable Delay
    Ji, Xunbi A.
    Molnar, Tamas G.
    Avedisov, Sergei S.
    Orosz, Gabor
    LEARNING FOR DYNAMICS AND CONTROL, VOL 120, 2020, 120 : 127 - 136
12345