图 书 馆
具有去噪的自动编码器的提取与组合鲁棒特征Extracting and Composing Robust Features with Denoising Autoencoders |
|
| 课程网址: | http://videolectures.net/icml08_vincent_ecrf/ |
| 主讲教师: | Pascal Vincent |
| 开课单位: | 蒙特利尔大学 |
| 开课时间: | 2008-08-29 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful itermediate representations. We introduce and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. This approach can be used to train autoencoders, and these denoising autoencoders can be stacked to initialize deep architectures. The algorithm can be motivated from a manifold learning and information theoretic perspective or from a generative model perspective. Comparative experiments clearly show the surprising advantage of corrupting the input of autoencoders on a pattern classification benchmark suite. |
| 关 键 词: | 无监督学习; 鲁棒性; 自动编码器 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-03：张荧(课程编辑志愿者) |
| 阅读次数: | 64 |