Improved Cleanup and Decoding of Fractional Power Encodings

Salvato in:
Dettagli Bibliografici
Pubblicato in:arXiv.org (Nov 30, 2024), p. n/a
Autore principale: Bremer, Alicia
Altri autori: Orchard, Jeff
Pubblicazione:
Cornell University Library, arXiv.org
Soggetti:
Accesso online:Citation/Abstract
Full text outside of ProQuest
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!

MARC

LEADER 00000nab a2200000uu 4500
001 3138994313
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3138994313 
045 0 |b d20241130 
100 1 |a Bremer, Alicia 
245 1 |a Improved Cleanup and Decoding of Fractional Power Encodings 
260 |b Cornell University Library, arXiv.org  |c Nov 30, 2024 
513 |a Working Paper 
520 3 |a High-dimensional vectors have been proposed as a neural method for representing information in the brain using Vector Symbolic Algebras (VSAs). While previous work has explored decoding and cleaning up these vectors under the noise that arises during computation, existing methods are limited. Cleanup methods are essential for robust computation within a VSA. However, cleanup methods for continuous-value encodings are not as effective. In this paper, we present an iterative optimization method to decode and clean up Fourier Holographic Reduced Representation (FHRR) vectors that are encoding continuous values. We combine composite likelihood estimation (CLE) and maximum likelihood estimation (MLE) to ensure convergence to the global optimum. We also demonstrate that this method can effectively decode FHRR vectors under different noise conditions, and show that it outperforms existing methods. 
653 |a Maximum likelihood estimation 
653 |a Computation 
653 |a Decoding 
653 |a Maximum likelihood decoding 
653 |a Cleaning 
700 1 |a Orchard, Jeff 
773 0 |t arXiv.org  |g (Nov 30, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3138994313/abstract/embedded/160PP4OP4BJVV2EV?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.00488