001051609 001__ 1051609
001051609 005__ 20260119203214.0
001051609 0247_ $$2arXiv$$aarXiv:2511.21674
001051609 037__ $$aFZJ-2026-00532
001051609 088__ $$2arXiv$$aarXiv:2511.21674
001051609 1001_ $$0P:(DE-Juel1)176282$$aKorcsak-Gorzo, Agnes$$b0$$eCorresponding author
001051609 245__ $$aEvent-driven eligibility propagation in large sparse networks: efficiency shaped by biological realism
001051609 260__ $$c2025
001051609 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1768822941_31203
001051609 3367_ $$2ORCID$$aWORKING_PAPER
001051609 3367_ $$028$$2EndNote$$aElectronic Article
001051609 3367_ $$2DRIVER$$apreprint
001051609 3367_ $$2BibTeX$$aARTICLE
001051609 3367_ $$2DataCite$$aOutput Types/Working Paper
001051609 520__ $$aDespite remarkable technological advances, AI systems may still benefit from biological principles, such as recurrent connectivity and energy-efficient mechanisms. Drawing inspiration from the brain, we present a biologically plausible extension of the eligibility propagation (e-prop) learning rule for recurrent spiking networks. By translating the time-driven update scheme into an event-driven one, we integrate the learning rule into a simulation platform for large-scale spiking neural networks and demonstrate its applicability to tasks such as neuromorphic MNIST. We extend the model with prominent biological features such as continuous dynamics and weight updates, strict locality, and sparse connectivity. Our results show that biologically grounded constraints can inform the design of computationally efficient AI algorithms, offering scalability to millions of neurons without compromising learning performance. This work bridges machine learning and computational neuroscience, paving the way for sustainable, biologically inspired AI systems while advancing our understanding of brain-like learning.
001051609 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001051609 536__ $$0G:(DE-Juel1)JL SMHB-2021-2027$$aJL SMHB - Joint Lab Supercomputing and Modeling for the Human Brain (JL SMHB-2021-2027)$$cJL SMHB-2021-2027$$x1
001051609 536__ $$0G:(DE-Juel-1)HiRSE_PS-20220812$$aHiRSE_PS - Helmholtz Platform for Research Software Engineering - Preparatory Study (HiRSE_PS-20220812)$$cHiRSE_PS-20220812$$x2
001051609 536__ $$0G:(DE-Juel1)BMBF-03ZU1106CB$$aBMBF 03ZU1106CB - NeuroSys: Algorithm-Hardware Co-Design (Projekt C) - B (BMBF-03ZU1106CB)$$cBMBF-03ZU1106CB$$x3
001051609 536__ $$0G:(EU-Grant)945539$$aHBP SGA3 - Human Brain Project Specific Grant Agreement 3 (945539)$$c945539$$fH2020-SGA-FETFLAG-HBP-2019$$x4
001051609 536__ $$0G:(EU-Grant)101147319$$aEBRAINS 2.0 - EBRAINS 2.0: A Research Infrastructure to Advance Neuroscience and Brain Health (101147319)$$c101147319$$fHORIZON-INFRA-2022-SERV-B-01$$x5
001051609 536__ $$0G:(DE-Juel1)jinb33_20220812$$aBrain-Scale Simulations (jinb33_20220812)$$cjinb33_20220812$$fBrain-Scale Simulations$$x6
001051609 588__ $$aDataset connected to arXivarXiv
001051609 7001_ $$0P:(DE-HGF)0$$aValverde, Jesús A. Espinoza$$b1
001051609 7001_ $$0P:(DE-Juel1)171475$$aStapmanns, Jonas$$b2
001051609 7001_ $$0P:(DE-Juel1)169781$$aPlesser, Hans Ekkehard$$b3$$ufzj
001051609 7001_ $$0P:(DE-Juel1)156459$$aDahmen, David$$b4$$ufzj
001051609 7001_ $$0P:(DE-HGF)0$$aBolten, Matthias$$b5
001051609 7001_ $$0P:(DE-Juel1)138512$$avan Albada, Sacha J.$$b6$$ufzj
001051609 7001_ $$0P:(DE-Juel1)144174$$aDiesmann, Markus$$b7$$ufzj
001051609 909CO $$ooai:juser.fz-juelich.de:1051609$$popenaire$$pVDB$$pec_fundedresources
001051609 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176282$$aForschungszentrum Jülich$$b0$$kFZJ
001051609 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)169781$$aForschungszentrum Jülich$$b3$$kFZJ
001051609 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)156459$$aForschungszentrum Jülich$$b4$$kFZJ
001051609 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)138512$$aForschungszentrum Jülich$$b6$$kFZJ
001051609 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)144174$$aForschungszentrum Jülich$$b7$$kFZJ
001051609 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$$x0
001051609 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lComputational and Systems Neuroscience$$x0
001051609 9201_ $$0I:(DE-Juel1)INM-10-20170113$$kINM-10$$lJara-Institut Brain structure-function relationships$$x1
001051609 980__ $$apreprint
001051609 980__ $$aVDB
001051609 980__ $$aI:(DE-Juel1)IAS-6-20130828
001051609 980__ $$aI:(DE-Juel1)INM-10-20170113
001051609 980__ $$aUNRESTRICTED