Abstract. We investigate bottom-up and top-down deterministic automata on unranked trees. We show that for an appropriate definition of bottom-up deterministic automata it is poss...
Active learning (AL) is an increasingly popular strategy for mitigating the amount of labeled data required to train classifiers, thereby reducing annotator effort. We describe ...
Byron C. Wallace, Kevin Small, Carla E. Brodley, T...
Image auto-annotation is an important open problem in
computer vision. For this task we propose TagProp, a discriminatively
trained nearest neighbor model. Tags of test
images a...
Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek...
Traditionally, the use of untranscribed speech has been restricted to unsupervised or semi-supervised training of acoustic models. Comparison of recognizers has required labeled d...
This paper presents a cooperative evolutionary approach for the problem of instance selection for instance based learning. The presented model takes advantage of one of the most r...