A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...
Prioritized sweeping is a model-based reinforcement learning method that attempts to focus an agent’s limited computational resources to achieve a good estimate of the value of ...
Service-oriented architectures and Web service infrastructure provide the ideal framework for interconnecting organizations and for defining distributed business applications. The...
: Tuning numerical libraries has become more difficult over time, as systems get more sophisticated. In particular, modern multicore machines make the behaviour of algorithms hard ...
Emmanuel Agullo, Jack Dongarra, Rajib Nath, Stanim...
We present a biology-inspired probabilistic graphical model, called the hypernetwork model, and its application to medical diagnosis of disease. The hypernetwork models are a way ...
JungWoo Ha, Jae-Hong Eom, Sung-Chun Kim, Byoung-Ta...