001024857 001__ 1024857 001024857 005__ 20250203103121.0 001024857 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-02523 001024857 037__ $$aFZJ-2024-02523 001024857 041__ $$aEnglish 001024857 1001_ $$0P:(DE-Juel1)201426$$aRenner, Alpha$$b0$$eCorresponding author$$ufzj 001024857 1112_ $$aInternational conference on neuromorphic, natural and physical computing$$cHannover$$d2023-10-25 - 2023-10-27$$gNNPC2023$$wGermany 001024857 245__ $$aNeuromorphic Hyperdimensional Visual Scene Factorization 001024857 260__ $$c2023 001024857 3367_ $$033$$2EndNote$$aConference Paper 001024857 3367_ $$2DataCite$$aOther 001024857 3367_ $$2BibTeX$$aINPROCEEDINGS 001024857 3367_ $$2DRIVER$$aconferenceObject 001024857 3367_ $$2ORCID$$aLECTURE_SPEECH 001024857 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1714563942_11807$$xAfter Call 001024857 520__ $$aIn this talk at NNPC 2023, I will present a modular neuromorphic algorithm leveraging recent advancements in hyperdimensional computing/ Vector Symbolic Architectures (VSAs).VSAs have been proposed as a framework for symbolic reasoning, spatial, and graph operations on neuromorphic hardware. They make use of a small set of computational primitives that are robust, efficient, and compatible with diverse hardware. Our algorithm approaches scene understanding as a factorization problem and employs the resonator network to extract object identities and transformations. This is achieved by reflecting the algebraic structure of 2d rigid transforms (translations and rotation) in the neural VSA representation. Finally, we use a spike-timing-based implementation of phasor neurons to show an efficient proof of concept implementation on neuromorphic hardware and employ the model in a robotics task for visual odometry (visual SLAM). 001024857 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0 001024857 7001_ $$0P:(DE-HGF)0$$aSupic, Lazar$$b1 001024857 7001_ $$0P:(DE-HGF)0$$aDanielescu, Andreea$$b2 001024857 7001_ $$0P:(DE-HGF)0$$aIndiveri, Giacomo$$b3 001024857 7001_ $$0P:(DE-HGF)0$$aOlshausen, Bruno A.$$b4 001024857 7001_ $$0P:(DE-HGF)0$$aSandamirskaya, Yulia$$b5 001024857 7001_ $$0P:(DE-HGF)0$$aSommer, Friedrich T.$$b6 001024857 7001_ $$0P:(DE-HGF)0$$aPaxon Frady, E.$$b7 001024857 8564_ $$uhttps://juser.fz-juelich.de/record/1024857/files/NNPC_2023_Hannover_abstract.pdf$$yOpenAccess 001024857 8564_ $$uhttps://juser.fz-juelich.de/record/1024857/files/NNPC_2023_Hannover_abstract.gif?subformat=icon$$xicon$$yOpenAccess 001024857 8564_ $$uhttps://juser.fz-juelich.de/record/1024857/files/NNPC_2023_Hannover_abstract.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess 001024857 8564_ $$uhttps://juser.fz-juelich.de/record/1024857/files/NNPC_2023_Hannover_abstract.jpg?subformat=icon-180$$xicon-180$$yOpenAccess 001024857 8564_ $$uhttps://juser.fz-juelich.de/record/1024857/files/NNPC_2023_Hannover_abstract.jpg?subformat=icon-640$$xicon-640$$yOpenAccess 001024857 909CO $$ooai:juser.fz-juelich.de:1024857$$pdriver$$pVDB$$popen_access$$popenaire 001024857 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)201426$$aForschungszentrum Jülich$$b0$$kFZJ 001024857 9131_ $$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 001024857 9141_ $$y2024 001024857 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess 001024857 920__ $$lyes 001024857 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0 001024857 980__ $$aconf 001024857 980__ $$aVDB 001024857 980__ $$aUNRESTRICTED 001024857 980__ $$aI:(DE-Juel1)PGI-15-20210701 001024857 9801_ $$aFullTexts