Please use this identifier to cite or link to this item:

Title: The learning problem of multi-layer neural networks
Authors: 班榮超
Ban, Jung-Chao
Chang, Chih-Hung
Contributors: 應數系
Keywords: Multi-layer neural networks;Topological entropy;Sofic shift;Learning problem;Linear separation
Date: 2013-01
Issue Date: 2020-06-22 13:45:11 (UTC+8)
Abstract: 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.
Relation: Neural Networks, Vol.46, pp.116-123
Data Type: article
DOI 連結:
Appears in Collections:[應用數學系] 期刊論文

Files in This Item:

File SizeFormat
125.pdf480KbAdobe PDF27View/Open

All items in 學術集成 are protected by copyright, with all rights reserved.

社群 sharing