The learning problem of multi-layer neural networks

被引:14
|
作者
Ban, Jung-Chao [1 ]
Chang, Chih-Hung [2 ]
机构
[1] Natl Dong Hwa Univ, Dept Appl Math, Hualien 970003, Taiwan
[2] Feng Chia Univ, Dept Appl Math, Taichung 40724, Taiwan
关键词
Multi-layer neural networks; Topological entropy; Sofic shift; Learning problem; Linear separation; PATTERN;
D O I
10.1016/j.neunet.2013.05.006
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This manuscript considers the learning problem of multi-layer neural networks (MNNs) with an activation function which comes from cellular neural networks. A systematic investigation of the partition of the parameter space is provided. Furthermore, the recursive formula of the transition matrix of an MNN is obtained. By implementing the well-developed tools in the symbolic dynamical systems, the topological entropy of an MNN can be computed explicitly. A novel phenomenon, the asymmetry of a topological diagram that was seen in Ban, Chang, Lin, and Lin (2009) [J. Differential Equations 246, pp. 552-580,2009], is revealed. (C) 2013 Elsevier Ltd. All rights reserved.
引用
收藏
页码:116 / 123
页数:8
相关论文
共 50 条
  • [1] Realization problem of multi-layer cellular neural networks
    Ban, Jung-Chao
    Chang, Chih-Hung
    NEURAL NETWORKS, 2015, 70 : 9 - 17
  • [2] Evolutionary learning algorithm for multi-layer morphological neural networks
    He, Chunmei
    Information Technology Journal, 2013, 12 (04) : 852 - 856
  • [3] An Adaptive Structure Learning Algorithm for Multi-Layer Spiking Neural Networks
    Wu, Doudou
    Lin, Xianghong
    Du, Pangao
    2019 15TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS 2019), 2019, : 98 - 102
  • [4] A new fast learning algorithm for multi-layer feedforward neural networks
    Zhang, De-Xian
    Liu, Can
    Wang, Zi-Qiang
    Liu, Nan-Bo
    PROCEEDINGS OF 2006 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2006, : 2928 - +
  • [5] A method of learning for multi-layer networks
    Tang, Z
    Wang, XG
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2002, E85A (02) : 522 - 525
  • [6] Ensemble learning for multi-layer networks
    Barber, D
    Bishop, CM
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 10, 1998, 10 : 395 - 401
  • [7] The layer effect on multi-layer cellular neural networks
    Ban, Jung-Chao
    Chang, Chih-Hung
    APPLIED MATHEMATICS LETTERS, 2013, 26 (07) : 706 - 709
  • [8] An algorithm for multi-layer channel routing problem using chaotic neural networks
    Ohta, M
    ISCAS 2000: IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS - PROCEEDINGS, VOL V: EMERGING TECHNOLOGIES FOR THE 21ST CENTURY, 2000, : 149 - 152
  • [9] On the structure of multi-layer cellular neural networks
    Ban, Jung-Chao
    Chang, Chih-Hung
    Lin, Song-Sun
    JOURNAL OF DIFFERENTIAL EQUATIONS, 2012, 252 (08) : 4563 - 4597
  • [10] Diamond in multi-layer cellular neural networks
    Ban, Jung-Chao
    Chang, Chih-Hung
    APPLIED MATHEMATICS AND COMPUTATION, 2013, 222 : 1 - 12