ADAPTATION OF APPLYING LAYER-WISE ADAPTIVE RATE SCALING (LARS) ON DISTRIBUTED MACHINE LEARNING MODEL
Distributed machine learning is one of the methods to speed up the training process by increasing the batch size. However, the use of large batch size tends to decrease accuracy due to the reduced number of iterations based on previous research. One of the methods to handle accuracy reduction due...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/74187 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |