11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Semi-Supervised Learning for Improved Expression of Uncertainty in Discriminative Classifiers

Jonathan Malkin, Jeff Bilmes

University of Washington, USA

Seeking classifier models that are not overconfident and that better represent the inherent uncertainty over a set of choices, we extend an objective for semi-supervised learning for neural networks to two models from the ratio semi-definite classifier (RSC) family. We show that the RSC family of classifiers produces smoother transitions between classes on a vowel classification task, and that the semi-supervised framework provides further benefits for smooth transitions. Finally, our testing methodology presents a novel way to evaluate the smoothness of classifier transitions (interpolating between vowels) by using samples from classes unseen during training time.

Full Paper

Bibliographic reference.  Malkin, Jonathan / Bilmes, Jeff (2010): "Semi-supervised learning for improved expression of uncertainty in discriminative classifiers", In INTERSPEECH-2010, 2990-2993.