001028218 001__ 1028218
001028218 005__ 20250204113906.0
001028218 0247_ $$2doi$$a10.1038/s42256-024-00848-0
001028218 0247_ $$2WOS$$aWOS:001258009300001
001028218 037__ $$aFZJ-2024-04412
001028218 041__ $$aEnglish
001028218 082__ $$a004
001028218 1001_ $$0P:(DE-Juel1)201426$$aRenner, Alpha$$b0$$eCorresponding author
001028218 245__ $$aNeuromorphic visual scene understanding with resonator networks
001028218 260__ $$aLondon$$bSpringer Nature Publishing$$c2024
001028218 3367_ $$2DRIVER$$aarticle
001028218 3367_ $$2DataCite$$aOutput Types/Journal article
001028218 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1734081742_7860
001028218 3367_ $$2BibTeX$$aARTICLE
001028218 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001028218 3367_ $$00$$2EndNote$$aJournal Article
001028218 520__ $$aAnalysing a visual scene by inferring the configuration of a generative model is widely considered the most flexible and generalizable approach to scene understanding. Yet, one major problem is the computational challenge of the inference procedure, involving a combinatorial search across object identities and poses. Here we propose a neuromorphic solution exploiting three key concepts: (1) a computational framework based on vector symbolic architectures (VSAs) with complex-valued vectors, (2) the design of hierarchical resonator networks to factorize the non-commutative transforms translation and rotation in visual scenes and (3) the design of a multi-compartment spiking phasor neuron model for implementing complex-valued resonator networks on neuromorphic hardware. The VSA framework uses vector binding operations to form a generative image model in which binding acts as the equivariant operation for geometric transformations. A scene can therefore be described as a sum of vector products, which can then be efficiently factorized by a resonator network to infer objects and their poses. The hierarchical resonator network features a partitioned architecture in which vector binding is equivariant for horizontal and vertical translation within one partition and for rotation and scaling within the other partition. The spiking neuron model allows mapping the resonator network onto efficient and low-power neuromorphic hardware. Our approach is demonstrated on synthetic scenes composed of simple two-dimensional shapes undergoing rigid geometric transformations and colour changes. A companion paper demonstrates the same approach in real-world application scenarios for machine vision and robotics.
001028218 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001028218 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001028218 7001_ $$00000-0002-3954-9688$$aSupic, Lazar$$b1
001028218 7001_ $$00000-0001-7460-2467$$aDanielescu, Andreea$$b2
001028218 7001_ $$00000-0002-7109-1689$$aIndiveri, Giacomo$$b3
001028218 7001_ $$0P:(DE-HGF)0$$aOlshausen, Bruno A.$$b4
001028218 7001_ $$00000-0003-4684-202X$$aSandamirskaya, Yulia$$b5
001028218 7001_ $$00000-0002-6738-9263$$aSommer, Friedrich T.$$b6$$eCorresponding author
001028218 7001_ $$00000-0001-8248-4544$$aFrady, E. Paxon$$b7$$eCorresponding author
001028218 773__ $$0PERI:(DE-600)2933875-X$$a10.1038/s42256-024-00848-0$$n6$$p641–652$$tNature machine intelligence$$v6$$x2522-5839$$y2024
001028218 8564_ $$uhttps://juser.fz-juelich.de/record/1028218/files/s42256-024-00848-0.pdf$$yRestricted
001028218 909CO $$ooai:juser.fz-juelich.de:1028218$$pVDB
001028218 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)201426$$aForschungszentrum Jülich$$b0$$kFZJ
001028218 9131_ $$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
001028218 9141_ $$y2024
001028218 915__ $$0StatID:(DE-HGF)3003$$2StatID$$aDEAL Nature$$d2023-08-29$$wger
001028218 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-08-29
001028218 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-08-29
001028218 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNAT MACH INTELL : 2022$$d2024-12-05
001028218 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-05
001028218 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-05
001028218 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-05
001028218 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2024-12-05
001028218 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-05
001028218 915__ $$0StatID:(DE-HGF)9920$$2StatID$$aIF >= 20$$bNAT MACH INTELL : 2022$$d2024-12-05
001028218 920__ $$lno
001028218 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001028218 980__ $$ajournal
001028218 980__ $$aVDB
001028218 980__ $$aI:(DE-Juel1)PGI-15-20210701
001028218 980__ $$aUNRESTRICTED