Logic Learning in Hopfield Networks

TL;DR

This paper experimentally compares Hebbian learning and Wan Abdullah's method for setting synaptic weights in Hopfield networks, demonstrating their equivalence through computer simulations.

Contribution

It provides an empirical evaluation of the equivalence between Hebbian learning and Wan Abdullah's method in Hopfield networks.

Findings

Hebbian learning and Wan Abdullah's method produce equivalent weights for the same program clauses

Experimental results confirm the theoretical equivalence between the two learning methods

The study enhances understanding of synaptic weight calculation in logic programming with neural networks

Abstract

Synaptic weights for neurons in logic programming can be calculated either by using Hebbian learning or by Wan Abdullah's method. In other words, Hebbian learning for governing events corresponding to some respective program clauses is equivalent with learning using Wan Abdullah's method for the same respective program clauses. In this paper we will evaluate experimentally the equivalence between these two types of learning through computer simulations.