Storing and Retrieving Data in a Parallel Distributed Memory System.

Abstract

The storage and retrieval of patterns in a Hopfield-like Parallel Distributed Memory is investigated experimentally with a view toward increasing its storage capacity. The first two Chapters give an overview of distributed memories and in particular the Hopfield distributed memory. This dissertation then experimentally investigates new and untested methods to increase the storage capabilities of a Hopfield-like neural net. Increasing the storage capacity by using the continuous-valued Hopfield memory is explored in Chapter 3 and the impact on capacity of data representation is experimentally investigated in Chapter 4. We then focus on new ways of storing data (changing the interconnect strengths) including in Chapter 7 developing a new method called Modifying the Energy Contour or MEC. In addition, this Chapter also outlines how to increase error-tolerance through the use of noisy patterns. The Hopfield distributed memory is then contrasted to another intelligent memory subsystem based on more of a traditional computer technology. In Chapter 8 we see that traditional computer technology using data-parallel techniques has a greater storage efficiency than possible with current Hopfield-like distributed memories.

Document Details

Document Type
Technical Report
Publication Date
Jun 09, 1987
Accession Number
ADA185177

Entities

People

  • Terry W. Potter

Organizations

  • Brown University

Tags

DTIC Thesaurus Topics

  • Computers
  • Efficiency

Readers

  • Neural Network Machine Learning.
  • Parallel and Distributed Computing.