001021872 001__ 1021872
001021872 005__ 20250203103350.0
001021872 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-01020
001021872 037__ $$aFZJ-2024-01020
001021872 041__ $$aEnglish
001021872 1001_ $$0P:(DE-Juel1)192147$$aLohoff, Jamie$$b0$$ufzj
001021872 1112_ $$anternational conference on neuromorphic, natural and physical computing$$cHanover$$d2023-10-25 - 2023-10-27$$gNNPC$$wGermany
001021872 245__ $$aFinding new bio-plausible Learning Rules using Deep Reinforcement Learning
001021872 260__ $$c2023
001021872 3367_ $$033$$2EndNote$$aConference Paper
001021872 3367_ $$2BibTeX$$aINPROCEEDINGS
001021872 3367_ $$2DRIVER$$aconferenceObject
001021872 3367_ $$2ORCID$$aCONFERENCE_POSTER
001021872 3367_ $$2DataCite$$aOutput Types/Conference Poster
001021872 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1710407181_31139$$xAfter Call
001021872 502__ $$cRWTH Aachen
001021872 520__ $$aGradient-based learning is still the best bet when training spiking neural networks on supervised tasks. Although backpropagation, the state-of-the-art in modern AI, is not bio-plausible, there exists a wide range of approximations with this property that achieve competitive performance, e.g. e-prop[1,2]. We propose a new framework called AlphaGrad that could find more such learning rules by systematically exploring the search space using Deep Reinforcement Learning and methods from Automatic Differentiation(AD).
001021872 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001021872 536__ $$0G:(DE-82)BMBF-16ME0398K$$aBMBF 16ME0398K - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0398K)$$cBMBF-16ME0398K$$x1
001021872 536__ $$0G:(DE-82)BMBF-16ME0399$$aBMBF 16ME0399 - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0399)$$cBMBF-16ME0399$$x2
001021872 7001_ $$0P:(DE-Juel1)188273$$aNeftci, Emre$$b1$$ufzj
001021872 8564_ $$uhttps://juser.fz-juelich.de/record/1021872/files/NNPC_poster.pdf$$yOpenAccess
001021872 8564_ $$uhttps://juser.fz-juelich.de/record/1021872/files/NNPC_poster.gif?subformat=icon$$xicon$$yOpenAccess
001021872 8564_ $$uhttps://juser.fz-juelich.de/record/1021872/files/NNPC_poster.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001021872 8564_ $$uhttps://juser.fz-juelich.de/record/1021872/files/NNPC_poster.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001021872 8564_ $$uhttps://juser.fz-juelich.de/record/1021872/files/NNPC_poster.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001021872 909CO $$ooai:juser.fz-juelich.de:1021872$$pdriver$$pVDB$$popen_access$$popenaire
001021872 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)192147$$aForschungszentrum Jülich$$b0$$kFZJ
001021872 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188273$$aForschungszentrum Jülich$$b1$$kFZJ
001021872 9131_ $$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
001021872 9141_ $$y2024
001021872 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001021872 920__ $$lyes
001021872 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001021872 980__ $$aposter
001021872 980__ $$aVDB
001021872 980__ $$aUNRESTRICTED
001021872 980__ $$aI:(DE-Juel1)PGI-15-20210701
001021872 9801_ $$aFullTexts