Evolving Spiking Neural Networks for online learning over drifting data streams

Simple item page
dc.contributor.authorLobo, Jesus L.
dc.contributor.authorLaƱa, Ibai
dc.contributor.authorDel Ser, Javier
dc.contributor.authorBilbao, Miren Nekane
dc.contributor.authorKasabov, Nikola
dc.contributor.institutionIA
dc.date.issued2018-12
dc.descriptionPublisher Copyright: Ā© 2018 Elsevier Ltd
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.statusPeer reviewed
dc.format.extent19
dc.format.extent1832264
dc.identifier.citationLobo , J L , LaƱa , I , Del Ser , J , Bilbao , M N & Kasabov , N 2018 , ' Evolving Spiking Neural Networks for online learning over drifting data streams ' , Neural Networks , vol. 108 , pp. 1-19 . https://doi.org/10.1016/j.neunet.2018.07.014
dc.identifier.doi10.1016/j.neunet.2018.07.014
dc.identifier.issn0893-6080
dc.identifier.otherresearchoutputwizard: 11556/643
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85051652590&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofNeural Networks
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsSpiking Neural Networks
dc.subject.keywordsData reduction
dc.subject.keywordsOnline learning
dc.subject.keywordsConcept drift
dc.subject.keywordsSpiking Neural Networks
dc.subject.keywordsData reduction
dc.subject.keywordsOnline learning
dc.subject.keywordsConcept drift
dc.subject.keywordsCognitive Neuroscience
dc.subject.keywordsArtificial Intelligence
dc.subject.keywordsFunding Info
dc.subject.keywordsThis work was supported by the EU project Pacific AtlanticNetwork for Technical Higher Education and Researchā€”PANTHER(grant number 2013-5659/004-001 EMA2).
dc.subject.keywordsThis work was supported by the EU project Pacific AtlanticNetwork for Technical Higher Education and Researchā€”PANTHER(grant number 2013-5659/004-001 EMA2).
dc.titleEvolving Spiking Neural Networks for online learning over drifting data streamsen
dc.typejournal article
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Evolving Spiking Neural Networks for online learning over drift.pdf
Size:
1.75 MB
Format:
Adobe Portable Document Format
Download