We show that temporal logic and combinations of temporal logics and modal logics of knowledge can be effectively represented in artificial neural networks. We present a Translat...
Abstract— We present an integrated vision and robotic system that plays, and learns to play, simple physically-instantiated board games that are variants of TIC TAC TOE and HEXAP...
Andrei Barbu, Siddharth Narayanaswamy, Jeffrey Mar...
Constructive induction divides the problem of learning an inductive hypothesis into two intertwined searches: one—for the “best” representation space, and two—for the “be...
—Methods for learning decision rules are being successfully applied to many problem domains, especially where understanding and interpretation of the learned model is necessary. ...
Learning Classifier Systems use evolutionary algorithms to facilitate rule- discovery, where rule fitness is traditionally payoff based and assigned under a sharing scheme. Most c...