001009239 001__ 1009239
001009239 005__ 20240313103129.0
001009239 037__ $$aFZJ-2023-02701
001009239 041__ $$aEnglish
001009239 1001_ $$0P:(DE-Juel1)174585$$aNestler, Sandra$$b0$$eCorresponding author$$ufzj
001009239 1112_ $$aSeminar Talk, Machine Learning Seminar$$cAachen$$d2023-07-13 - 2023-07-13$$wGermany
001009239 245__ $$aA statistical perspective on learning of time series in neural networks$$f2023-07-13 - 
001009239 260__ $$c2023
001009239 3367_ $$033$$2EndNote$$aConference Paper
001009239 3367_ $$2DataCite$$aOther
001009239 3367_ $$2BibTeX$$aINPROCEEDINGS
001009239 3367_ $$2ORCID$$aLECTURE_SPEECH
001009239 3367_ $$0PUB:(DE-HGF)31$$2PUB:(DE-HGF)$$aTalk (non-conference)$$btalk$$mtalk$$s1689925979_19178$$xInvited
001009239 3367_ $$2DINI$$aOther
001009239 520__ $$aIn this talk, we explore a statistical perspective on learning in neural networks, drawing inspiration from both neuroscience and machine learning. We investigate the stochastic nature of neural activity and stimuli and utilize tools from statistical physics to address these aspects. The focus lies on the time-dependent processing of stimuli.Recurrent neural networks, a concept inspired by the brain, handle time series naturally. For weakly non-linear interactions, a method is developed to approximate network dynamics, leading to improved performance in a random recurrent reservoir. For the scenario of linear interactions, we investigate how the optimal classifier balances stability and performance in the presence of background noise.We then study how non-linear interactions shape the statistical processing of stimuli, demonstrating a direct relationship between non-linearity, representation, and higher-order statistics using a single-layer perceptron. Moreover, we explore learning the data distribution itself, employing an invertible neural network (normalizing flows) to extract informative modes. This unsupervised approach uncovers underlying structure, dimensionality, and meaningful latent features in the data.
001009239 536__ $$0G:(DE-HGF)POF4-5231$$a5231 - Neuroscientific Foundations (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001009239 536__ $$0G:(DE-HGF)POF4-5232$$a5232 - Computational Principles (POF4-523)$$cPOF4-523$$fPOF IV$$x1
001009239 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x2
001009239 536__ $$0G:(EU-Grant)945539$$aHBP SGA3 - Human Brain Project Specific Grant Agreement 3 (945539)$$c945539$$fH2020-SGA-FETFLAG-HBP-2019$$x3
001009239 536__ $$0G:(DE-HGF)SO-092$$aACA - Advanced Computing Architectures (SO-092)$$cSO-092$$x4
001009239 536__ $$0G:(DE-Juel-1)BMBF-01IS19077A$$aRenormalizedFlows - Transparent Deep Learning with Renormalized Flows (BMBF-01IS19077A)$$cBMBF-01IS19077A$$x5
001009239 536__ $$0G:(DE-Juel-1)PF-JARA-SDS005$$aSDS005 - Towards an integrated data science of complex natural systems (PF-JARA-SDS005)$$cPF-JARA-SDS005$$x6
001009239 536__ $$0G:(DE-82)EXS-SF-neuroIC002$$aneuroIC002 - Recurrence and stochasticity for neuro-inspired computation (EXS-SF-neuroIC002)$$cEXS-SF-neuroIC002$$x7
001009239 536__ $$0G:(GEPRIS)368482240$$aGRK 2416 - GRK 2416: MultiSenses-MultiScales: Neue Ansätze zur Aufklärung neuronaler multisensorischer Integration (368482240)$$c368482240$$x8
001009239 7001_ $$0P:(DE-Juel1)171384$$aKeup, Christian$$b1$$ufzj
001009239 7001_ $$0P:(DE-Juel1)156459$$aDahmen, David$$b2$$ufzj
001009239 7001_ $$0P:(DE-Juel1)184621$$aGilson, Matthieu$$b3
001009239 7001_ $$0P:(DE-HGF)0$$aRauhut, Holger$$b4
001009239 7001_ $$0P:(DE-HGF)0$$aBoutaib, Youness$$b5
001009239 7001_ $$0P:(DE-Juel1)178725$$aBouss, Peter$$b6$$ufzj
001009239 7001_ $$0P:(DE-Juel1)184900$$aMerger, Claudia Lioba$$b7$$ufzj
001009239 7001_ $$0P:(DE-Juel1)180150$$aFischer, Kirsten$$b8$$ufzj
001009239 7001_ $$0P:(DE-Juel1)178936$$aRene, Alexandre$$b9$$ufzj
001009239 7001_ $$0P:(DE-Juel1)144806$$aHelias, Moritz$$b10$$ufzj
001009239 8564_ $$uhttps://juser.fz-juelich.de/record/1009239/files/A%20statistical%20perspective%20on%20learning%20of%20time%20series%20in%20neural%20networks.pptx$$yRestricted
001009239 909CO $$ooai:juser.fz-juelich.de:1009239$$pec_fundedresources$$pVDB$$popenaire
001009239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)174585$$aForschungszentrum Jülich$$b0$$kFZJ
001009239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171384$$aForschungszentrum Jülich$$b1$$kFZJ
001009239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)156459$$aForschungszentrum Jülich$$b2$$kFZJ
001009239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178725$$aForschungszentrum Jülich$$b6$$kFZJ
001009239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)184900$$aForschungszentrum Jülich$$b7$$kFZJ
001009239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180150$$aForschungszentrum Jülich$$b8$$kFZJ
001009239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178936$$aForschungszentrum Jülich$$b9$$kFZJ
001009239 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)144806$$aForschungszentrum Jülich$$b10$$kFZJ
001009239 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$$x0
001009239 9131_ $$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
001009239 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$$x2
001009239 9141_ $$y2023
001009239 920__ $$lyes
001009239 9201_ $$0I:(DE-Juel1)INM-6-20090406$$kINM-6$$lComputational and Systems Neuroscience$$x0
001009239 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lTheoretical Neuroscience$$x1
001009239 9201_ $$0I:(DE-Juel1)INM-10-20170113$$kINM-10$$lJara-Institut Brain structure-function relationships$$x2
001009239 980__ $$atalk
001009239 980__ $$aVDB
001009239 980__ $$aI:(DE-Juel1)INM-6-20090406
001009239 980__ $$aI:(DE-Juel1)IAS-6-20130828
001009239 980__ $$aI:(DE-Juel1)INM-10-20170113
001009239 980__ $$aUNRESTRICTED
001009239 981__ $$aI:(DE-Juel1)IAS-6-20130828