Newton Methods For Convolutional Neural Networks
碩士 === 國立臺灣大學 === 資訊網路與多媒體研究所 === 106 === Deep learning involves a difficult non-convex optimization problem, which is often solved by stochastic gradient (SG) methods. While SG is usually effective, it is sometimes not very robust. Recently, Newton methods have been investigated as an alternative o...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2018
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/52es69 |