Distributed B-SDLM: accelerating the training convergence of deep neural networks through parallelism
This paper proposes an efficient asynchronous stochastic second order learning algorithm for distributed learning of neural networks (NNs). The proposed algorithm, named distributed bounded stochastic diagonal Levenberg-Marquardt (distributed B-SDLM), is based on the B-SDLM algorithm that converges...
Disimpan dalam:
| Pengarang-pengarang Utama: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Diterbitkan: |
Springer Verlag
2016
|
| Subjek-subjek: | |
| Capaian Atas Talian: | http://eprints.utm.my/73608/ http://eprints.utm.my/73608/ |
| Penanda-penanda: |
Tambah Penanda
Tiada Penanda, Jadilah orang pertama menanda rekod ini!
|