One of the primary issues with traditional anomaly detection approaches is their inability to handle complex, structural data. One approach to this issue involves the detection of...
A neural net with multiple output nodes is capable of distinguishing among a set of related input classes even in the absence of training. It can do so with an accuracy that is ma...
In this paper, we investigate the hypothesis that plan recognition can significantly improve the performance of a casebased reinforcement learner in an adversarial action selectio...
Researchers in commonsense, qualitative spatial and temporal reasoning (QSTR) provide flexible and intuitive methods for reasoning about vague and uncertain information including ...
In our experiments with four well-known systems for solving partially observable planning problems (Contingent-FF, MBP, PKS, and POND), we were greatly surprised to find that they...
Ronald Alford, Ugur Kuter, Dana S. Nau, Elnatan Re...