On Neural Associative Memory Structures: Storage and Retrieval of Sequences in a Chain of Tournaments
dc.contributor.author | Abolpour Mofrad, Asieh | |
dc.contributor.author | Abolpour Mofrad, Samaneh | |
dc.contributor.author | Yazidi, Anis | |
dc.contributor.author | Parker, Matthew Geoffrey | |
dc.date.accessioned | 2022-04-25T14:03:12Z | |
dc.date.available | 2022-04-25T14:03:12Z | |
dc.date.created | 2021-09-10T15:59:18Z | |
dc.date.issued | 2021 | |
dc.identifier.issn | 0899-7667 | |
dc.identifier.uri | https://hdl.handle.net/11250/2992618 | |
dc.description.abstract | Associative memories enjoy many interesting properties in terms of error correction capabilities, robustness to noise, storage capacity, and retrieval performance, and their usage spans over a large set of applications. In this letter, we investigate and extend tournament-based neural networks, originally proposed by Jiang, Gripon, Berrou, and Rabbat (2016), a novel sequence storage associative memory architecture with high memory efficiency and accurate sequence retrieval. We propose a more general method for learning the sequences, which we call feedback tournament-based neural networks. The retrieval process is also extended to both directions: forward and backward—in other words, any large-enough segment of a sequence can produce the whole sequence. Furthermore, two retrieval algorithms, cache-winner and explore-winner, are introduced to increase the retrieval performance. Through simulation results, we shed light on the strengths and weaknesses of each algorithm. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | MIT Press | en_US |
dc.title | On Neural Associative Memory Structures: Storage and Retrieval of Sequences in a Chain of Tournaments | en_US |
dc.type | Journal article | en_US |
dc.type | Peer reviewed | en_US |
dc.description.version | publishedVersion | en_US |
dc.rights.holder | Copyright 2021 Massachusetts Institute of Technology | en_US |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.fulltext | postprint | |
cristin.qualitycode | 2 | |
dc.identifier.doi | 10.1162/neco_a_01417 | |
dc.identifier.cristin | 1933339 | |
dc.source.journal | Neural Computation | en_US |
dc.source.pagenumber | 2550-2577 | en_US |
dc.identifier.citation | Neural Computation. 2021, 33 (9), 2550-2577. | en_US |
dc.source.volume | 33 | en_US |
dc.source.issue | 9 | en_US |
Files in this item
This item appears in the following Collection(s)
-
Department of Informatics [978]
-
Registrations from Cristin [10237]