咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >Hausdorff Dimension of Multi-L... 收藏

Hausdorff Dimension of Multi-Layer Neural Networks

Hausdorff Dimension of Multi-Layer Neural Networks

作     者:Jung-Chao Ban Chih-Hung Chang 

作者机构:Department of Applied Mathematics Feng Chia University Taichung Taiwan Department of Applied Mathematics National Dong Hwa University Hualien Taiwan 

出 版 物:《Advances in Pure Mathematics》 (理论数学进展(英文))

年 卷 期:2013年第3卷第9期

页      面:9-14页

学科分类:07[理学] 0701[理学-数学] 070101[理学-基础数学] 

主  题:Multi-Layer Neural Networks Hausdorff Dimension Sofic Shift Output Space 

摘      要: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.

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分