We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
Equivocation has been widely used as a measure of security after Shannon[10]. For an infinite system such as the wiretap channel defined in [2], equivocation is unbounded and so e...
Background: Identifying functional elements, such as transcriptional factor binding sites, is a fundamental step in reconstructing gene regulatory networks and remains a challengi...
Weichun Huang, David M. Umbach, Uwe Ohler, Leping ...
We define the concept of dependence among multiple variables using maximum entropy techniques and introduce a graphical notation to denote the dependencies. Direct inference of in...
We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language trans...
Yuqing Gao, Bowen Zhou, Zijian Diao, Jeffrey S. So...