图 书 馆
学习特征层次的学习深度生成模型Learning Feature Hierarchies by Learning Deep Generative Models |
|
| 课程网址: | http://videolectures.net/nipsworkshops09_salakhutdinov_lfhldgm/ |
| 主讲教师: | Ruslan Salakhutdinov |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2010-03-26 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | In this paper we present several ideas based on learning deep generative models from high-dimensional, richly structured sensory input. We will exploit the following two key properties: First, we show that deep generative models can be learned efficiently from large amounts of unlabeled data. Second, they can be discriminatively fine-tuned using the standard backpropagation algorithm. Our results reveal that the learned high-level feature representations capture a lot of structure in the unlabeled input data, which is useful for subsequent discriminative tasks, such as classification or regression, even though these tasks are unknown when the deep generative model is being trained. |
| 关 键 词: | 特征选择; 模型; 机器学习 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-29：wuyq |
| 阅读次数: | 34 |