A New Training Algorithm for Kanerva's Sparse Distributed Memory

TL;DR

This paper introduces a novel training algorithm for Kanerva's Sparse Distributed Memory that improves its efficiency with non-random data and enables recognition of inverted patterns, expanding its applicability beyond random data handling.

Contribution

It presents a new training approach and a different method for creating hard locations in SDM, enhancing its performance with structured data and pattern recognition capabilities.

Findings

Enhanced handling of non-random data in SDM

Ability to recognize inverted patterns

Different method for creating hard locations

Abstract

The Sparse Distributed Memory proposed by Pentii Kanerva (SDM in short) was thought to be a model of human long term memory. The architecture of the SDM permits to store binary patterns and to retrieve them using partially matching patterns. However Kanerva's model is especially efficient only in handling random data. The purpose of this article is to introduce a new approach of training Kanerva's SDM that can handle efficiently non-random data, and to provide it the capability to recognize inverted patterns. This approach uses a signal model which is different from the one proposed for different purposes by Hely, Willshaw and Hayes in [4]. This article additionally suggests a different way of creating hard locations in the memory despite the Kanerva's static model.