Show simple item record

dc.contributor.authorTyukin, Ivan Y.
dc.contributor.authorGorban, Alexander N.
dc.contributor.authorMcEwan, Alistair A.
dc.contributor.authorMeshkinfamfard, Sepehr
dc.contributor.authorTang, Lixin
dc.date.accessioned2021-03-22T14:22:06Z
dc.date.available2021-03-22T14:22:06Z
dc.date.issued2021-02-03
dc.identifier.citationTyukin, 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.en_US
dc.identifier.issn0020-0255
dc.identifier.doi10.1016/j.ins.2021.01.022
dc.identifier.urihttp://hdl.handle.net/10545/625663
dc.description.abstractIn 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.en_US
dc.description.sponsorshipMinistry of Education and Science of the Russian Federationen_US
dc.language.isoenen_US
dc.publisherElsevier BVen_US
dc.relation.urlhttps://www.sciencedirect.com/science/article/pii/S0020025521000499?via%3Dihuben_US
dc.rights.urihttps://www.elsevier.com/tdm/userlicense/1.0/
dc.subjectControl and Systems Engineeringen_US
dc.subjectTheoretical Computer Scienceen_US
dc.subjectSoftwareen_US
dc.subjectInformation Systems and Managementen_US
dc.subjectArtificial Intelligenceen_US
dc.subjectComputer Science Applicationsen_US
dc.titleBlessing of dimensionality at the edge and geometry of few-shot learningen_US
dc.typeArticleen_US
dc.contributor.departmentUniversity of Leicesteren_US
dc.contributor.departmentLobachevsky University, Russiaen_US
dc.contributor.departmentSt Petersburg State Electrotechnical University, Russiaen_US
dc.contributor.departmentUniversity College Londonen_US
dc.contributor.departmentNortheastern University, Chinaen_US
dc.contributor.departmentNorwegian University of Science and Technology, Norwayen_US
dc.contributor.departmentUniversity of Derbyen_US
dc.identifier.journalInformation Sciencesen_US
dc.identifier.piiS0020025521000499
dc.source.journaltitleInformation Sciences
dcterms.dateAccepted2021-01-08
dc.author.detail300938en_US


Files in this item

Thumbnail
Name:
Publisher version

This item appears in the following Collection(s)

Show simple item record