Burles, Nathan John orcid.org/0000-0003-3030-1675, O'Keefe, Simon orcid.org/0000-0001-5957-2474, Austin, Jim orcid.org/0000-0001-5762-8614 et al. (1 more author) (2013) ENAMeL : a language for binary correlation matrix memories:reducing the memory constraints of matrix memories. Neural Processing Letters. pp. 1-23. ISSN 1573-773X
Abstract
Despite their relative simplicity, Correlation Matrix Memories (CMMs) are an active area of research, as they are able to be integrated into more complex architectures such as the Associative Rule Chaining Architecture (ARCA) [1]. In this architecture, CMMs are used effectively in order to reduce the time complexity of a tree search from O(bd) to O(d)—where b is the branching factor and d is the depth of the tree. This paper introduces the Extended Neural Associative Memory Language (ENAMeL)—a domain specific language developed to ease development of applications using correlation matrix memories (CMMs). We discuss various considerations required while developing the language, and techniques used to reduce the memory requirements of CMM-based applications. Finally we show that the memory requirements of ARCA when using the ENAMeL interpreter compare favourably to our original results [1] run in MATLAB.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | Pure (York) |
Date Deposited: | 08 Apr 2014 15:00 |
Last Modified: | 08 Jan 2025 00:04 |
Published Version: | https://doi.org/10.1007/s11063-013-9307-8 |
Status: | Published |
Refereed: | Yes |
Identification Number: | 10.1007/s11063-013-9307-8 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:75671 |
Download
Filename: enamel_final.pdf
Description: ENAMeL: A Language for Binary Correlation Matrix Memories