Neural Network Capacity for Multilevel Inputs

TL;DR

This paper investigates how multilevel inputs and new learning strategies can significantly enhance the memory capacity of Hopfield neural networks, enabling better pattern recall and scalability.

Contribution

It introduces novel learning strategies that increase Hopfield network capacity and analyzes their scalability with network size.

Findings

Multilevel inputs substantially increase network capacity.

New learning strategies improve pattern recall.

Capacity scales favorably with network size.

Abstract

This paper examines the memory capacity of generalized neural networks. Hopfield networks trained with a variety of learning techniques are investigated for their capacity both for binary and non-binary alphabets. It is shown that the capacity can be much increased when multilevel inputs are used. New learning strategies are proposed to increase Hopfield network capacity, and the scalability of these methods is also examined in respect to size of the network. The ability to recall entire patterns from stimulation of a single neuron is examined for the increased capacity networks.