Logic Programming In Neural Networks

Abstract

Logic programming is carried out on a neural network. A higher-order Hopfield neural network is used to minimise logical inconsistency in interpretations of logic clauses or programs. The connection strengths are defined from the logic program; the network relaxes to neural states corresponding to a valid (or near-valid) interpretation. ?Creativity? can be thought of as the crossing of configurational energy barriers to arrive at alternative interpretations. The formalism allows the incorporation of non-monotonicity; non-integral degrees of truth in rules; and non-Horn clauses. Hebbian learning in an environment with some underlying logical rules governing events is equivalent to hardwiring the network with these rules