- Improvement of Generalization Ability of Deep CNN via Implicit Regularization in Two-Stage Training Process
- 点击次数:
- 所属单位:信息科学与工程学院
- 发表刊物: IEEE Access
- 关键字:Deep CNN;image classification;overfitting;generalization;anomaly detection;implicit regularization
- 第一作者:郑庆河
- 论文编号:1395247996840448001
- 卷号:6
- 页面范围:15844-15869
- 字数:5000
- 是否译文:否
- 发表时间:2018-01-01