000906138 001__ 906138
000906138 005__ 20240313103121.0
000906138 0247_ $$2doi$$a10.1186/s13662-022-03686-9
000906138 0247_ $$2Handle$$a2128/30882
000906138 0247_ $$2WOS$$aWOS:000867408700002
000906138 037__ $$aFZJ-2022-01251
000906138 082__ $$a510
000906138 1001_ $$00000-0002-2032-2512$$aBoutaib, Youness$$b0$$eCorresponding author
000906138 245__ $$aPath classification by stochastic linear recurrent neural networks
000906138 260__ $$aLondon . BioMed Central$$c2022
000906138 3367_ $$2DRIVER$$aarticle
000906138 3367_ $$2DataCite$$aOutput Types/Journal article
000906138 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1648201229_2173
000906138 3367_ $$2BibTeX$$aARTICLE
000906138 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000906138 3367_ $$00$$2EndNote$$aJournal Article
000906138 520__ $$aWe investigate the functioning of a classifying biological neural network from the perspective of statistical learning theory, modelled, in a simplified setting, as a continuous-time stochastic recurrent neural network (RNN) with the identity activation function. In the purely stochastic (robust) regime, we give a generalisation error bound that holds with high probability, thus showing that the empirical risk minimiser is the best-in-class hypothesis. We show that RNNs retain a partial signature of the paths they are fed as the unique information exploited for training and classification tasks. We argue that these RNNs are easy to train and robust and support these observations with numerical experiments on both synthetic and real data. We also show a trade-off phenomenon between accuracy and robustness.
000906138 536__ $$0G:(DE-HGF)POF4-5231$$a5231 - Neuroscientific Foundations (POF4-523)$$cPOF4-523$$fPOF IV$$x0
000906138 536__ $$0G:(DE-HGF)POF4-5232$$a5232 - Computational Principles (POF4-523)$$cPOF4-523$$fPOF IV$$x1
000906138 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x2
000906138 536__ $$0G:(DE-82)EXS-SF-neuroIC002$$aneuroIC002 - Recurrence and stochasticity for neuro-inspired computation (EXS-SF-neuroIC002)$$cEXS-SF-neuroIC002$$x3
000906138 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000906138 7001_ $$0P:(DE-HGF)0$$aBartolomaeus, Wiebke$$b1
000906138 7001_ $$0P:(DE-Juel1)174585$$aNestler, Sandra$$b2$$ufzj
000906138 7001_ $$0P:(DE-HGF)0$$aRauhut, Holger$$b3$$eLast author
000906138 773__ $$0PERI:(DE-600)3112904-3$$a10.1186/s13662-022-03686-9$$gVol. 2022, no. 1, p. 13$$n1$$p13$$tAdvances in continuous and discrete models$$v2022$$x2731-4235$$y2022
000906138 8564_ $$uhttps://juser.fz-juelich.de/record/906138/files/Path%20classification%20by%20stochastic%20linear%20recurrent%20neural%20networks.pdf$$yOpenAccess
000906138 909CO $$ooai:juser.fz-juelich.de:906138$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000906138 9101_ $$0I:(DE-588b)36225-6$$60000-0002-2032-2512$$aRWTH Aachen$$b0$$kRWTH
000906138 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b1$$kRWTH
000906138 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)174585$$aForschungszentrum Jülich$$b2$$kFZJ
000906138 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b3$$kRWTH
000906138 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5231$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x0
000906138 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5232$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x1
000906138 9131_ $$0G:(DE-HGF)POF4-523$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5234$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vNeuromorphic Computing and Network Dynamics$$x2
000906138 9141_ $$y2022
000906138 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000906138 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000906138 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-24
000906138 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-24
000906138 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-24
000906138 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-24
000906138 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2022-11-24
000906138 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bADV DIFFER EQU-NY : 2021$$d2022-11-24
000906138 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-02-14T16:18:18Z
000906138 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-02-14T16:18:18Z
000906138 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2021-02-14T16:18:18Z
000906138 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2022-11-24
000906138 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2022-11-24
000906138 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2022-11-24
000906138 9201_ $$0I:(DE-Juel1)INM-6-20090406$$kINM-6$$lComputational and Systems Neuroscience$$x0
000906138 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lTheoretical Neuroscience$$x1
000906138 9201_ $$0I:(DE-Juel1)INM-10-20170113$$kINM-10$$lJara-Institut Brain structure-function relationships$$x2
000906138 9801_ $$aFullTexts
000906138 980__ $$ajournal
000906138 980__ $$aVDB
000906138 980__ $$aUNRESTRICTED
000906138 980__ $$aI:(DE-Juel1)INM-6-20090406
000906138 980__ $$aI:(DE-Juel1)IAS-6-20130828
000906138 980__ $$aI:(DE-Juel1)INM-10-20170113
000906138 981__ $$aI:(DE-Juel1)IAS-6-20130828