Adadb: Adaptive Diff-Batch Optimization Technique for Gradient Descent
Gradient descent is the workhorse of deep neural networks. Gradient descent has the disadvantage of slow convergence. The famous way to overcome slow convergence is to use momentum. Momentum effectively increases the learning factor of gradient descent. Recently, many approaches have been proposed t...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Artigo |
| Sprache: | Inglês |
| Veröffentlicht: |
IEEE
2021-01-01
|
| Schriftenreihe: | IEEE Access |
| Schlagworte: | |
| Online-Zugang: | https://ieeexplore.ieee.org/document/9481902/ |
| Tags: |
Keine Tags, Fügen Sie das erste Tag hinzu!
|