Self-organization on a sphere with application to topological ordering of Chinese characters

Andrew P. Paplinski

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

    Abstract

    We consider a case of self-organization in which a relatively small number N of data points is mapped on a larger number M of nodes. This is a reverse situation to a typical clustering problem when a node represents a center of the cluster of data points. In our case the objective is to have a Gaussian-like distribution of weights over nodes in the neighbourhood of the winner for a given stimulus. The fact that M > N creates some problem with using learning schemes related to Gaussian MixtureModels.We also show how the objects, Chinese characters in our case, can be topologically ordered on a surface of a 3D sphere. A Chinese character is represented by an angular integral of the Radon Transform (aniRT) which is an RTS-invariant 1-D signature function of an image.

    Original languageEnglish
    Title of host publicationNeural Information Processing
    Subtitle of host publication23rd International Conference, ICONIP 2016, Kyoto, Japan, October 16-21, 2016, Proceedings, Part IV
    EditorsAkira Hirose, Seiichi Ozawa, Kenji Doya, Kazushi Ikeda, Minho Lee, Derong Liu
    PublisherSpringer
    Pages452-459
    Number of pages8
    ISBN (Electronic)9783319466811
    ISBN (Print)9783319466804
    DOIs
    Publication statusPublished - 2016
    EventInternational Conference on Neural Information Processing 2016 - Kyoto, Japan
    Duration: 16 Oct 201621 Oct 2016
    Conference number: 23rd
    https://link.springer.com/conference/iconip

    Publication series

    NameLecture Notes in Computer Science
    Volume9950
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Conference

    ConferenceInternational Conference on Neural Information Processing 2016
    Abbreviated titleICONIP 2016
    CountryJapan
    CityKyoto
    Period16/10/1621/10/16
    Otherfour-volume proceedings of the 23rd International Conference
    on Neural Information Processing (ICONIP 2016) held in Kyoto, Japan, during
    October 16–21, 2016

    Lecture Notes in Computer Science 9947
    Neural Information Processing
    23rd International Conference, ICONIP 2016
    Kyoto, Japan, October 16–21, 2016
    Proceedings, Part I
    ISSN 0302-9743 ISSN 1611-3349 (electronic)
    Lecture Notes in Computer Science
    ISBN 978-3-319-46686-6 ISBN 978-3-319-46687-3 (eBook)
    DOI 10.1007/978-3-319-46687-3
    Internet address

    Keywords

    • Angular integral of the radon transform
    • Gaussian mixture models
    • Probabilistic self-organizing maps
    • Self-organization on a sphere

    Cite this