• Login
    View Item 
    •   Home
    • Research Publications
    • Engineering & Technology
    • Department of Electronics, Computing & Maths
    • View Item
    •   Home
    • Research Publications
    • Engineering & Technology
    • Department of Electronics, Computing & Maths
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of UDORACommunitiesTitleAuthorsIssue DateSubmit DateSubjectsThis CollectionTitleAuthorsIssue DateSubmit DateSubjects

    My Account

    LoginRegister

    About and further information

    AboutOpen Access WebpagesPublication and Open Access PolicyTake Down Policy University Privacy NoticeUniversity NewsTools for ResearchersLibraryUDo

    Statistics

    Display statistics

    Blessing of dimensionality at the edge and geometry of few-shot learning

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Publisher version
    View Source
    Access full-text PDFOpen Access
    View Source
    Check access options
    Check access options
    Authors
    Tyukin, Ivan Y.
    Gorban, Alexander N.
    McEwan, Alistair A.
    Meshkinfamfard, Sepehr
    Tang, Lixin
    Affiliation
    University of Leicester
    Lobachevsky University, Russia
    St Petersburg State Electrotechnical University, Russia
    University College London
    Northeastern University, China
    Norwegian University of Science and Technology, Norway
    University of Derby
    Issue Date
    2021-02-03
    
    Metadata
    Show full item record
    Abstract
    In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a priori quantifiable guarantees – or more specifically remove classification errors – over time. This is distinct from state-of-the-art machine learning, AI, and software approaches. The theory enables building few-shot AI correction algorithms and provides conditions justifying their successful application. Another feature of this approach is that, in the supervised setting, the computational complexity of training is linear in the number of training samples. At the time of classification, the computational complexity is bounded by few inner product calculations. Moreover, the implementation is shown to be very scalable. This makes it viable for deployment in applications where computational power and memory are limited, such as embedded environments. It enables the possibility for fast on-line optimisation using improved training samples. The approach is based on the concentration of measure effects and stochastic separation theorems and is illustrated with an example on the identification faulty processes in Computer Numerical Control (CNC) milling and with a case study on adaptive removal of false positives in an industrial video surveillance and analytics system.
    Citation
    Tyukin, I.Y., Gorban, A.N., McEwan, A.A., Meshkinfamfard, S. and Tang, L., 2021. Blessing of dimensionality at the edge and geometry of few-shot learning. Information Sciences, 564, pp. 124-143.
    Publisher
    Elsevier BV
    Journal
    Information Sciences
    URI
    http://hdl.handle.net/10545/625663
    DOI
    10.1016/j.ins.2021.01.022
    Additional Links
    https://www.sciencedirect.com/science/article/pii/S0020025521000499?via%3Dihub
    Type
    Article
    Language
    en
    ISSN
    0020-0255
    ae974a485f413a2113503eed53cd6c53
    10.1016/j.ins.2021.01.022
    Scopus Count
    Collections
    Department of Electronics, Computing & Maths

    entitlement

     
    DSpace software (copyright © 2002 - 2021)  DuraSpace
    Quick Guide | Contact Us
    Open Repository is a service operated by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.