A novel architecture for capturing discrete sequences using self-organizing maps

Manjusri Ishwara, Jayantha Rajapakse, Damminda Alahakoon

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    Abstract

    This paper, proposes a layered approach to capture discrete sequences by exploiting the best matching unit (BMU) selection process of the self-organizing map (SOM) to generate a finite state machine (FSM). The FSM is used with thresholding to identify prominent subsequences available in input data.
    Original languageEnglish
    Title of host publicationNeural Information Processing: 21st International Conference (ICONIP 2014)
    Subtitle of host publicationKuching, Malaysia, November 3-6, 2014, Proceedings, Part I
    EditorsChu Kiong Loo, Keem Siah Yap, Kok Wai Wong, Andrew Teoh, Kaizhu Huang
    Place of PublicationCham, Switzerland
    PublisherSpringer
    Pages551-558
    Number of pages8
    ISBN (Print)9783319126364
    DOIs
    Publication statusPublished - 2014
    EventInternational Conference on Neural Information Processing 2014 - Kuching, Malaysia
    Duration: 3 Nov 20146 Nov 2014
    Conference number: 21st
    https://link.springer.com/book/10.1007/978-3-319-12637-1

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume8834
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Conference

    ConferenceInternational Conference on Neural Information Processing 2014
    Abbreviated titleICONIP 2014
    Country/TerritoryMalaysia
    CityKuching
    Period3/11/146/11/14
    Internet address

    Cite this