Hausdorff Dimension of Multi-Layer Neural Networks

doi:10.4236/apm.2013.39A1002

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | Items with full text/Total items : 94586/125118 (76%)
Visitors : 30547490 Online Users : 337

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer

政大機構典藏 > 理學院 > 應用數學系 > 期刊論文 > Item 140.119/129558

Please use this identifier to cite or link to this item: http://nccur.lib.nccu.edu.tw/handle/140.119/129558

Title:	Hausdorff Dimension of Multi-Layer Neural Networks
Authors:	班榮超 Ban, Jung-Chao Chang, Chih-Hung
Contributors:	應數系
Keywords:	Multi-Layer Neural Networks;Hausdorff Dimension;Sofic Shift;Output Space
Date:	2013-11
Issue Date:	2020-04-28 13:55:07 (UTC+8)
Abstract:	This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, the Hausdorff dimension of the output space relates to its topological entropy. This clarifies the geometrical structure of the output space in more details.
Relation:	Advances in Pure Mathematics, 2013, 3, 9-14
Data Type:	article
DOI 連結:	https://doi.org/10.4236/apm.2013.39A1002
DOI:	10.4236/apm.2013.39A1002
Appears in Collections:	[應用數學系] 期刊論文

Files in This Item:

File	Size	Format
193.pdf	203Kb	Adobe PDF	23	View/Open

社群 sharing

著作權政策宣告

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。

Loading...