We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...
Dong Yu, Balakrishnan Varadarajan, Li Deng, Alex A...
Abstract—We present a general scheme for learning sensorimotor tasks which allows rapid on-line learning and generalization of the learned knowledge to unfamiliar objects. The sc...
Transfer learning addresses the problem of how to leverage knowledge acquired in a source domain to improve the accuracy and speed of learning in a related target domain. This pap...
Lilyana Mihalkova, Tuyen N. Huynh, Raymond J. Moon...
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supe...
One of the most contemporary research ideas for adaptive web-based educational systems is personalizing the educational contents, based on users’ learning styles. Moreover, it i...