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...
Disimpan dalam:
| Pengarang-pengarang Utama: | , , |
|---|---|
| Format: | Artikel |
| Diterbitkan: |
Elsevier B.V.
2016
|
| Subjek-subjek: | |
| Capaian Atas Talian: | http://eprints.utm.my/71140/ http://eprints.utm.my/71140/ |
| Penanda-penanda: |
Tambah Penanda
Tiada Penanda, Jadilah orang pertama menanda rekod ini!
|