Show simple item record

dc.contributor.authorAbolpour Mofrad, Asieh
dc.contributor.authorAbolpour Mofrad, Samaneh
dc.contributor.authorYazidi, Anis
dc.contributor.authorParker, Matthew Geoffrey
dc.date.accessioned2022-04-25T14:03:12Z
dc.date.available2022-04-25T14:03:12Z
dc.date.created2021-09-10T15:59:18Z
dc.date.issued2021
dc.identifier.issn0899-7667
dc.identifier.urihttps://hdl.handle.net/11250/2992618
dc.description.abstractAssociative 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.isoengen_US
dc.publisherMIT Pressen_US
dc.titleOn Neural Associative Memory Structures: Storage and Retrieval of Sequences in a Chain of Tournamentsen_US
dc.typeJournal articleen_US
dc.typePeer revieweden_US
dc.description.versionpublishedVersionen_US
dc.rights.holderCopyright 2021 Massachusetts Institute of Technologyen_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.fulltextpostprint
cristin.qualitycode2
dc.identifier.doi10.1162/neco_a_01417
dc.identifier.cristin1933339
dc.source.journalNeural Computationen_US
dc.source.pagenumber2550-2577en_US
dc.identifier.citationNeural Computation. 2021, 33 (9), 2550-2577.en_US
dc.source.volume33en_US
dc.source.issue9en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record