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