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

来源：

NEURAL NETWORKS | 2013年 / 46卷

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

页码：116 / 123

页数：8

共 50 条

[21] Distributed Training for Multi-Layer Neural Networks by Consensus
Liu, Bo
Ding, Zhengtao
Lv, Chen
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (05) : 1771 - 1778
[22] Minimal Multi-Layer Modifications of Deep Neural Networks
Refaeli, Idan
Katz, Guy
SOFTWARE VERIFICATION AND FORMAL METHODS FOR ML-ENABLED AUTONOMOUS SYSTEMS, FOMLAS 2022, NSV 2022, 2022, 13466 : 46 - 66
[23] Application of multi-layer neural networks to image compression
Ahmed, OA
Fahmy, MM
ISCAS '97 - PROCEEDINGS OF 1997 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS I - IV: CIRCUITS AND SYSTEMS IN THE INFORMATION AGE, 1997, : 1273 - 1276
[24] RECURSIVE ASSEMBLY OF MULTI-LAYER PERCEPTRON NEURAL NETWORKS
Motato, Eliot
Radcliffe, Clark
7TH ANNUAL DYNAMIC SYSTEMS AND CONTROL CONFERENCE, 2014, VOL 2, 2014,
[25] The effects of quantization on multi-layer feedforward neural networks
Jiang, MG
Gielen, G
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2003, 17 (04) : 637 - 661
[26] Adaptive Multi-layer Contrastive Graph Neural Networks
Shuhao Shi
Pengfei Xie
Xu Luo
Kai Qiao
Linyuan Wang
Jian Chen
Bin Yan
Neural Processing Letters, 2023, 55 : 4757 - 4776
[27] The Spatial Complexity of Inhomogeneous Multi-layer Neural Networks
Jung-Chao Ban
Chih-Hung Chang
Neural Processing Letters, 2016, 43 : 31 - 47
[28] The Spatial Complexity of Inhomogeneous Multi-layer Neural Networks
Ban, Jung-Chao
Chang, Chih-Hung
NEURAL PROCESSING LETTERS, 2016, 43 (01) : 31 - 47
[29] Adaptive Multi-layer Contrastive Graph Neural Networks
Shi, Shuhao
Xie, Pengfei
Luo, Xu
Qiao, Kai
Wang, Linyuan
Chen, Jian
Yan, Bin
NEURAL PROCESSING LETTERS, 2023, 55 (04) : 4757 - 4776
[30] Multi-layer neural networks applied to distance relaying
Department of Electrical Engineering, University of São Paulo, EESC/USP Av. Dr. C. Botelho, 1465, 13560-250-São Carlos , Brazil
Int J Electr Power Energy Syst, 8 (539-542):

← 1 2 3 4 5 →