Delta Learning Rule for the Active Sites Model

TL;DR

This paper introduces a delta learning rule for the Active Sites model to enhance memory capacity and extends the binary neural network to a multi-level system, comparing it with the Hebbian approach.

Contribution

It develops a delta rule for the Active Sites model and extends binary neural networks to multi-level, improving memory capacity and comparison methods.

Findings

Increased memory capacity with the delta rule

Successful extension to multi-level neural networks

Enhanced comparison of learning rules

Abstract

This paper reports the results on methods of comparing the memory retrieval capacity of the Hebbian neural network which implements the B-Matrix approach, by using the Widrow-Hoff rule of learning. We then, extend the recently proposed Active Sites model by developing a delta rule to increase memory capacity. Also, this paper extends the binary neural network to a multi-level (non-binary) neural network.