Show simple item record

dc.contributor.authorLobo, Jesus L.
dc.contributor.authorLaña, Ibai
dc.contributor.authorDel Ser, Javier
dc.contributor.authorBilbao, Miren Nekane
dc.contributor.authorKasabov, Nikola
dc.date.accessioned2018-11-13T09:33:11Z
dc.date.available2018-11-13T09:33:11Z
dc.date.issued2018-12
dc.identifier.citationLobo, Jesus L., Ibai Laña, Javier Del Ser, Miren Nekane Bilbao, and Nikola Kasabov. “Evolving Spiking Neural Networks for Online Learning over Drifting Data Streams.” Neural Networks 108 (December 2018): 1–19. doi:10.1016/j.neunet.2018.07.014.en
dc.identifier.issn0893-6080en
dc.identifier.urihttp://hdl.handle.net/11556/643
dc.description.abstractNowadays huge volumes of data are produced in the form of fast streams, which are further affected by non-stationary phenomena. The resulting lack of stationarity in the distribution of the produced data calls for efficient and scalable algorithms for online analysis capable of adapting to such changes (concept drift). The online learning field has lately turned its focus on this challenging scenario, by designing incremental learning algorithms that avoid becoming obsolete after a concept drift occurs. Despite the noted activity in the literature, a need for new efficient and scalable algorithms that adapt to the drift still prevails as a research topic deserving further effort. Surprisingly, Spiking Neural Networks, one of the major exponents of the third generation of artificial neural networks, have not been thoroughly studied as an online learning approach, even though they are naturally suited to easily and quickly adapting to changing environments. This work covers this research gap by adapting Spiking Neural Networks to meet the processing requirements that online learning scenarios impose. In particular the work focuses on limiting the size of the neuron repository and making the most of this limited size by resorting to data reduction techniques. Experiments with synthetic and real data sets are discussed, leading to the empirically validated assertion that, by virtue of a tailored exploitation of the neuron repository, Spiking Neural Networks adapt better to drifts, obtaining higher accuracy scores than naive versions of Spiking Neural Networks for online learning environments.en
dc.description.sponsorshipThis work was supported by the EU project Pacific AtlanticNetwork for Technical Higher Education and Research—PANTHER(grant number 2013-5659/004-001 EMA2).en
dc.language.isoengen
dc.publisherElsevier Ltden
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.titleEvolving Spiking Neural Networks for online learning over drifting data streamsen
dc.typejournal articleen
dc.identifier.doi10.1016/j.neunet.2018.07.014en
dc.rights.accessRightsembargoed accessen
dc.subject.keywordsSpiking Neural Networksen
dc.subject.keywordsData reductionen
dc.subject.keywordsOnline learningen
dc.subject.keywordsConcept driften
dc.journal.titleNeural Networksen
dc.page.final19en
dc.page.initial1en
dc.volume.number108en


Files in this item

Thumbnail

    Show simple item record

    Attribution-NonCommercial-NoDerivatives 4.0 InternationalExcept where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International