This paper analyses the possibilities of integrating different technological and knowledge representation techniques for the development of a framework for the remote control of mu...
Dale Dzemydiene, Antanas Andrius Bielskis, Arunas ...
Assume that we are trying to build a visual recognizer for a particular class of objects--chairs, for example--using existing induction methods. Assume the assistance of a human t...
Many approaches to active learning involve periodically training one classifier and choosing data points with the lowest confidence. An alternative approach is to periodically cho...
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
Real world images often contain similar objects but with different rotations, noise, or other visual alterations. Vision systems should be able to recognize objects regardless of ...