| dc.contributor | 應數系 | - |
| dc.creator (作者) | 班榮超 | - |
| dc.creator (作者) | Ban, Jung-Chao | - |
| dc.creator (作者) | Chang, Chih-Hung | - |
| dc.date (日期) | 2013-01 | - |
| dc.date.accessioned | 22-Jun-2020 13:45:11 (UTC+8) | - |
| dc.date.available | 22-Jun-2020 13:45:11 (UTC+8) | - |
| dc.date.issued (上傳時間) | 22-Jun-2020 13:45:11 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/130212 | - |
| dc.description.abstract (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. | - |
| dc.format.extent | 491685 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.relation (關聯) | Neural Networks, Vol.46, pp.116-123 | - |
| dc.subject (關鍵詞) | Multi-layer neural networks ; Topological entropy ; Sofic shift ; Learning problem ; Linear separation | - |
| dc.title (題名) | The learning problem of multi-layer neural networks | - |
| dc.type (資料類型) | article | - |
| dc.identifier.doi (DOI) | 10.1016/j.neunet.2013.05.006 | - |
| dc.doi.uri (DOI) | https://doi.org/10.1016/j.neunet.2013.05.006 | - |
