0


学习验证的复杂性

The Complexity of Learning Verification
课程网址: http://videolectures.net/nc04_langford_clv/  
主讲教师: John Langford
开课单位: 微软公司
开课时间: 2007-02-25
课程语种: 英语
中文简介:
非正式地,学习理论的一个分支侧重于制作“这种学习的分类器至少是X好”形式的陈述。这种形式的许多界限背后的共同直觉是,在所有分类器的集合中必须存在某种形式的“先验”或“偏见”才能做出这样的陈述。这种直觉可以通过几种形式精确化。我将讨论“偏见”和“先验”允许可验证学习的方式以及解决此问题的“先验”的局限性。
课程简介: Informally, one branch of learning theory focuses on making statements of the form 'this learned classifier is at least X good'. A common intuition underlying many bounds of this form is that some form of 'prior' or 'bias' must exist on the set of all classifiers in order to make such statements. This intuition can be made precise in a few forms. I'll discuss the ways by which 'bias' and 'prior' allow verifiable learning as well as the limitations of 'prior' in addressing this problem.
关 键 词: 共同直觉; 可验证学习; 先验局限性
课程来源: 视频讲座网
最后编审: 2020-06-08:吴雨秋(课程编辑志愿者)
阅读次数: 63