Dynamic fine‐tuning layer selection using Kullback–Leibler divergence
Abstract The selection of layers in the transfer learning fine‐tuning process ensures a pre‐trained model's accuracy and adaptation in a new target domain. However, the selection process is still manual and without clearly defined criteria. If the wrong layers in a neural network are selected a...
| 出版年: | Engineering Reports |
|---|---|
| 主要な著者: | , , |
| フォーマット: | 論文 |
| 言語: | 英語 |
| 出版事項: |
Wiley
2023-05-01
|
| 主題: | |
| オンライン･アクセス: | https://doi.org/10.1002/eng2.12595 |