In general, the best explanation for a given observation makes no promises on how good it is with respect to other alternative explana tions. A major deficiency of message-passing schemes for belief revision in Bayesian net works is their inability to generate alterna tives beyond the second best. In this pa per, we present a general approach based on linear constraint systems that naturally gen erates alternative explanations in an orderly and highly efficient manner. This approach is then applied to cost-based abduction prob lems as well as belief revision in Bayesian net works.

No abstract

No abstract

Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. AbstractModern elements of military intelligence and decision making require predictions of adversary force actions and reactions to provide a complete and realistic viewpoint. Current methods for providing realistic adversary force simulation are largely manual processes. Adversarial simulation requires continual assessment of friendly courses of action and is currently "human assessment capability" limited. To develop a computational model of dynamic adversary behaviors that includes the ability to integrate with intelligence and mission data sources, computational models must address operational patterns, behaviors, or doctrines of present-day adversaries (terrorist cells, local insurgents, guerillas, and armed thugs) as well as more conventional force elements. The dynamic nature of adversary force behavior with respect to the changing capabilities, biases, beliefs, goals, intentions, and perceptions of friendly force actions must be addressed. The Emergent Adversarial Modeling System (EAMS) addresses these elements through explicit focus on adversarial intent as a driver for adversarial response. Specific capabilities address the changing nature of adversary composition. This paper will discuss the results of the ongoing EAMS research project into adversarial modeling and adversarial response simulation.