Because observing the same actions can warrant different conclusions depending on who executed the actions, a goal recognizer that works well on one person might not work well on ...
This paper presents an algorithm for extract ing propositions from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural networ...
Implementing new operating systems is tedious, costly, and often impractical except for large projects. The Flux OSKit addresses this problem in a novel way by providing clean, we...
Bryan Ford, Godmar Back, Greg Benson, Jay Lepreau,...
One of the key issues in reasoning with multiple interacting intelligent agents is how to model and code the decision making process of the agents. In Artificial Intelligence (AI...
Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be address...