Improving Deep Neural Networks by Using Sparse Dropout Strategy
文献类型：会议论文
| 作者 | Zheng Hao ; Mingming Chen; Wenju Liu; Zhanlei Yang; Shan Liang; Hao Zheng
|
| 出版日期 | 2014 |
| 会议日期 | 2014 |
| 会议地点 | Xi an, Shanxi, China |
| 关键词 | Dropout Sparse Dropout Deep Neural Networks Deep Learning |
| 英文摘要 | Recently, deep neural networks(DNNs) have achieved excelleng results on benchmarks for acoustic modeling of speech recognition. By randomly discarding network units, a strategy which is called as dropout can improve the performance of DNNs by reducing the influence of over-fitting. However, the random dropout strategy treats units indiscriminately, which may lose information on distributions of units outputs. In this paper, we improve the dropout strategy by differential treatment to units according to their outputs. Only minor changes to an existing neural network system can achieve a significant improvement. Experiments of phone recognition on TIMIT show that the sparse dropout fine-tuning gets significant performance improvement.; Recently, deep neural networks(DNNs) have achieved excelleng results on benchmarks for acoustic modeling of speech recognition. By randomly discarding network units, a strategy which is called as dropout can improve the performance of DNNs by reducing the influence of over-fitting. However, the random dropout strategy treats units indiscriminately, which may lose information on distributions of units outputs. In this paper, we improve the dropout strategy by differential treatment to units according to their outputs. Only minor changes to an existing neural network system can achieve a significant improvement. Experiments of phone recognition on TIMIT show that the sparse dropout fine-tuning gets significant performance improvement. |
| 会议录 | ChinaSIP
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/11776]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_机器人视觉团队 |
| 通讯作者 | Hao Zheng |
| 作者单位 | National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
| 推荐引用方式 GB/T 7714 | Zheng Hao,Mingming Chen,Wenju Liu,et al. Improving Deep Neural Networks by Using Sparse Dropout Strategy[C]. 见:. Xi an, Shanxi, China. 2014. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。