机器学习中的理论与实践的相互作用 - 新兴的理论挑战Theory-Practice Interplay in Machine Learning – Emerging Theoretical Challenges |
|
课程网址: | http://videolectures.net/ecmlpkdd09_ben_david_tpim/ |
主讲教师: | Shai Ben-David |
开课单位: | 滑铁卢大学 |
开课时间: | 信息不详。欢迎您在右侧留言补充。 |
课程语种: | 英语 |
中文简介: | 理论分析在统计机器学习的一些最显著的实际成功中发挥了重要作用。然而,主流机器学习理论假定一些强简化假设,这些假设往往是不现实的。在过去的十年中,机器学习的实践已经导致了各种启发式范例的发展,这些范例可以满足日益广泛的应用程序的需求。许多有用的这样的范例超出了目前可用的分析范围。理论在新出现的机器学习子领域中也会发挥类似的关键作用吗?在这篇演讲中,我将调查一些应用激发的理论挑战。特别是,我将讨论半监督学习、多任务学习、“学习到学习”、隐私保护学习等理论分析的最新进展。 |
课程简介: | Theoretical analysis has played a major role in some of the most prominent practical successes of statistical machine learning. However, mainstream machine learning theory assumes some strong simplifying assumptions which are often unrealistic. In the past decade, the practice of machine learning has led to the development of various heuristic paradigms that answer the needs of a vastly growing range of applications. Many useful such paradigms fall beyond the scope of the currently available analysis. Will theory play a similar pivotal role in the newly emerging sub areas of machine learning? In this talk, I will survey some such application-motivated theoretical challenges. In particular, I will discuss recent developments in the theoretical analysis of semi-supervised learning, multi-task learning, “learning to learn”, privacy-preserving learning and more. |
关 键 词: | 机器学习; 理论学习; 实践学习 |
课程来源: | 视频讲座网 |
最后编审: | 2019-12-05:cwx |
阅读次数: | 35 |