001047373 001__ 1047373
001047373 005__ 20251111202158.0
001047373 0247_ $$2doi$$a10.48550/arXiv.2510.19764
001047373 037__ $$aFZJ-2025-04262
001047373 1001_ $$0P:(DE-HGF)0$$aKnight, James C.$$b0
001047373 245__ $$aA flexible framework for structural plasticity in GPU-accelerated sparse spiking neural networks
001047373 260__ $$barXiv$$c2025
001047373 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1762844415_31627
001047373 3367_ $$2ORCID$$aWORKING_PAPER
001047373 3367_ $$028$$2EndNote$$aElectronic Article
001047373 3367_ $$2DRIVER$$apreprint
001047373 3367_ $$2BibTeX$$aARTICLE
001047373 3367_ $$2DataCite$$aOutput Types/Working Paper
001047373 520__ $$aThe majority of research in both training Artificial Neural Networks (ANNs) and modeling learning in biological brains focuses on synaptic plasticity, where learning equates to changing the strength of existing connections. However, in biological brains, structural plasticity - where new connections are created and others removed - is also vital, not only for effective learning but also for recovery from damage and optimal resource usage. Inspired by structural plasticity, pruning is often used in machine learning to remove weak connections from trained models to reduce the computational requirements of inference. However, the machine learning frameworks typically used for backpropagation-based training of both ANNs and Spiking Neural Networks (SNNs) are optimized for dense connectivity, meaning that pruning does not help reduce the training costs of ever-larger models. The GeNN simulator already supports efficient GPU-accelerated simulation of sparse SNNs for computational neuroscience and machine learning. Here, we present a new flexible framework for implementing GPU-accelerated structural plasticity rules and demonstrate this first using the e-prop supervised learning rule and DEEP R to train efficient, sparse SNN classifiers and then, in an unsupervised learning context, to learn topographic maps. Compared to baseline dense models, our sparse classifiers reduce training time by up to 10x while the DEEP R rewiring enables them to perform as well as the original models. We demonstrate topographic map formation in faster-than-realtime simulations, provide insights into the connectivity evolution, and measure simulation speed versus network size. The proposed framework will enable further research into achieving and maintaining sparsity in network structure and neural communication, as well as exploring the computational benefits of sparsity in a range of neuromorphic applications.
001047373 536__ $$0G:(DE-HGF)POF4-5232$$a5232 - Computational Principles (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001047373 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x1
001047373 536__ $$0G:(EU-Grant)945539$$aHBP SGA3 - Human Brain Project Specific Grant Agreement 3 (945539)$$c945539$$fH2020-SGA-FETFLAG-HBP-2019$$x2
001047373 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$$x3
001047373 588__ $$aDataset connected to DataCite
001047373 650_7 $$2Other$$aNeural and Evolutionary Computing (cs.NE)
001047373 650_7 $$2Other$$aNeurons and Cognition (q-bio.NC)
001047373 650_7 $$2Other$$aFOS: Computer and information sciences
001047373 650_7 $$2Other$$aFOS: Biological sciences
001047373 7001_ $$0P:(DE-Juel1)162130$$aSenk, Johanna$$b1$$eCorresponding author$$ufzj
001047373 7001_ $$0P:(DE-HGF)0$$aNowotny, Thomas$$b2
001047373 773__ $$a10.48550/arXiv.2510.19764$$tarXiv$$y2025
001047373 8564_ $$uhttps://doi.org/10.48550/arXiv.2510.19764
001047373 8564_ $$uhttps://juser.fz-juelich.de/record/1047373/files/2510.19764v1.pdf$$yRestricted
001047373 909CO $$ooai:juser.fz-juelich.de:1047373$$popenaire$$pVDB$$pec_fundedresources
001047373 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)162130$$aForschungszentrum Jülich$$b1$$kFZJ
001047373 9131_ $$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$$vNeuromorphic Computing and Network Dynamics$$x0
001047373 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$$x1
001047373 9141_ $$y2025
001047373 920__ $$lno
001047373 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lComputational and Systems Neuroscience$$x0
001047373 980__ $$apreprint
001047373 980__ $$aVDB
001047373 980__ $$aI:(DE-Juel1)IAS-6-20130828
001047373 980__ $$aUNRESTRICTED