Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems
This paper focuses on the enhancement of the generalization ability and training stability of deep neural networks (DNNs). New activation functions that we call bounded rectified linear unit (ReLU), bounded leaky ReLU, and bounded bi-firing are proposed. These activation functions are defined based...
Saved in:
| Main Authors: | , , |
|---|---|
| 格式: | Article |
| 出版: |
Elsevier B.V.
2016
|
| 主题: | |
| 在线阅读: | http://eprints.utm.my/id/eprint/71140/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-84994477344&doi=10.1016%2fj.neucom.2016.08.037&partnerID=40&md5=5b940413f14332dd63cda37f4ebfbe4b |
| 标签: |
添加标签
没有标签, 成为第一个标记此记录!
|
成为第一个发表评论!