Back to Search Start Over

Efficient Decoding of Compositional Structure in Holistic Representations.

Authors :
Kleyko, Denis
Bybee, Connor
Huang, Ping-Chen
Kymn, Christopher J.
Olshausen, Bruno A.
Frady, E. Paxon
Sommer, Friedrich T.
Source :
Neural Computation. Jul2023, Vol. 35 Issue 7, p1159-1186. 28p. 1 Diagram, 1 Chart, 3 Graphs.
Publication Year :
2023

Abstract

We investigate the task of retrieving information from compositional distributed representations formed by hyperdimensional computing/vector symbolic architectures and present novel techniques that achieve new information rate bounds. First, we provide an overview of the decoding techniques that can be used to approach the retrieval task. The techniques are categorized into four groups. We then evaluate the considered techniques in several settings that involve, for example, inclusion of external noise and storage elements with reduced precision. In particular, we find that the decoding techniques from the sparse coding and compressed sensing literature (rarely used for hyperdimensional computing/vector symbolic architectures) are also well suited for decoding information from the compositional distributed representations. Combining these decoding techniques with interference cancellation ideas from communications improves previously reported bounds (Hersche et al., 2021) of the information rate of the distributed representations from 1.20 to 1.40 bits per dimension for smaller codebooks and from 0.60 to 1.26 bits per dimension for larger codebooks. [ABSTRACT FROM AUTHOR]

Subjects

Subjects :
*NOISE
*STORAGE
*LITERATURE
*SENSES

Details

Language :
English
ISSN :
08997667
Volume :
35
Issue :
7
Database :
Academic Search Index
Journal :
Neural Computation
Publication Type :
Academic Journal
Accession number :
164277200
Full Text :
https://doi.org/10.1162/neco_a_01590