图 书 馆
深度核仁Deep-er Kernels |
|
| 课程网址: | http://videolectures.net/roks2013_shawe_taylor_kernels/ |
| 主讲教师: | John Shawe-Taylor |
| 开课单位: | 伦敦大学 |
| 开课时间: | 2013-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  由于仅将学习应用于单个（输出）层，因此可以将内核视为较浅的内核。深度网络的最新成功凸显了需要考虑功能更丰富的类的需求。演讲将回顾和讨论为使更丰富的内核类能够被学习而开发的方法。尽管其中一些方法依赖贪婪过程，但统计学习分析和/或收敛范围支持了许多方法。演讲将强调在该主题上进行进一步研究的潜力。 |
| 课程简介: | Kernels can be viewed as shallow in that learning is only applied in a single (output) layer. Recent successes with deeper networks highlight the need to consider richer function classes. The talk will review and discuss methods that have been developed to enable richer kernel classes to be learned. While some of these methods rely on greedy procedures many are supported by statistical learning analyses and/or convergence bounds. The talk will highlight the potential for further research on this topic. |
| 关 键 词: | 统计学习分析; 学习内核 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-10-29：zyk |
| 最后编审: | 2020-10-29：zyk |
| 阅读次数: | 45 |