In this paper, we present a new decompositional approach for the extraction of propositional rules from feed-forward neural networks of binary threshold units. After decomposing t...
For probabilistic reasoning, one often needs to sample from a combinatorial space. For example, one may need to sample uniformly from the space of all satisfying assignments. Can ...
: A multi-level hypermap interface was created for the display of world wide web pages relevant to an undergraduate class in Sensation and Perception. Assessment of the interface c...
Each concept description language and search strategy has an inherent inductive bias, a preference for some hypotheses over others. No single inductive bias performs optimally on ...
David K. Tcheng, Bruce L. Lambert, Stephen C. Y. L...
We investigate planning for self-interested agents in large multi-agent simulations. We present two heuristic algorithms that exploit different domain-specific properties in order...