An adaptive semi-supervised ensemble method, ASSEMBLE, is proposed that constructs classification ensembles based on both labeled and unlabeled data. ASSEMBLE alternates between a...
Abstract We propose in this paper a novel approach to the classification of discrete sequences. This approach builds a model fitting some dynamical features deduced from the learni...
Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning ...
Current evaluation functions for heuristic planning are expensive to compute. In numerous planning problems these functions provide good guidance to the solution, so they are wort...
For a Boolean formula on n variables, the associated property P is the collection of n-bit strings that satisfy . We study the query complexity of tests that distinguish (with hig...
Eli Ben-Sasson, Prahladh Harsha, Sofya Raskhodniko...