So far, tractable planning problems reported in the literature have been defined by syntactical restrictions. To better exploit the inherent structure in problems, however, it is ...
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...
We present a new algorithm for eliminating excess parameters and improving network generalization after supervised training. The method, \Principal Components Pruning (PCP)",...
This paper concerns the task of removing redundant information from a given knowledge base, and restructuring it in the form of a tree, so as to admit efficient problem solving ro...
A constraint satisfaction problem, or CSP, can be reformulated as an integer linear programming problem. The reformulated problem can be solved via polynomial multiplication. If t...