Generalized Expectation Criteria
暂无分享,去创建一个
This note describes generalized expectation (GE) criteria, a framework for incorporating preferences about model expectations into parameter estimation objective functions. We discuss relations to other methods, various learning paradigms it supports, and applications that can leverage its flexibility.
[1] Gideon S. Mann,et al. Leveraging Existing Resources using Generalized Expectation Criteria , 2007 .
[2] Gideon S. Mann,et al. Simple, robust, scalable semi-supervised learning via expectation regularization , 2007, ICML '07.
[3] Gideon S. Mann,et al. Reducing Annotation Effort Using Generalized Expectation Criteria , 2007 .