001038223 001__ 1038223
001038223 005__ 20250203103321.0
001038223 0247_ $$2doi$$a10.48550/ARXIV.2408.15800
001038223 037__ $$aFZJ-2025-01259
001038223 1001_ $$0P:(DE-Juel1)195754$$aStewart, Kenneth$$b0
001038223 245__ $$aEmulating Brain-like Rapid Learning in Neuromorphic Edge Computing
001038223 260__ $$barXiv$$c2024
001038223 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1738573093_11958
001038223 3367_ $$2ORCID$$aWORKING_PAPER
001038223 3367_ $$028$$2EndNote$$aElectronic Article
001038223 3367_ $$2DRIVER$$apreprint
001038223 3367_ $$2BibTeX$$aARTICLE
001038223 3367_ $$2DataCite$$aOutput Types/Working Paper
001038223 520__ $$aAchieving personalized intelligence at the edge with real-time learning capabilities holds enormous promise in enhancing our daily experiences and helping decision making, planning, and sensing. However, efficient and reliable edge learning remains difficult with current technology due to the lack of personalized data, insufficient hardware capabilities, and inherent challenges posed by online learning. Over time and across multiple developmental stages, the brain has evolved to efficiently incorporate new knowledge by gradually building on previous knowledge. In this work, we emulate the multiple stages of learning with digital neuromorphic technology that simulates the neural and synaptic processes of the brain using two stages of learning. First, a meta-training stage trains the hyperparameters of synaptic plasticity for one-shot learning using a differentiable simulation of the neuromorphic hardware. This meta-training process refines a hardware local three-factor synaptic plasticity rule and its associated hyperparameters to align with the trained task domain. In a subsequent deployment stage, these optimized hyperparameters enable fast, data-efficient, and accurate learning of new classes. We demonstrate our approach using event-driven vision sensor data and the Intel Loihi neuromorphic processor with its plasticity dynamics, achieving real-time one-shot learning of new classes that is vastly improved over transfer learning. Our methodology can be deployed with arbitrary plasticity models and can be applied to situations demanding quick learning and adaptation at the edge, such as navigating unfamiliar environments or learning unexpected categories of data through user engagement.
001038223 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001038223 588__ $$aDataset connected to DataCite
001038223 650_7 $$2Other$$aNeural and Evolutionary Computing (cs.NE)
001038223 650_7 $$2Other$$aArtificial Intelligence (cs.AI)
001038223 650_7 $$2Other$$aFOS: Computer and information sciences
001038223 7001_ $$0P:(DE-HGF)0$$aNeumeier, Michael$$b1
001038223 7001_ $$0P:(DE-HGF)0$$aShrestha, Sumit Bam$$b2
001038223 7001_ $$0P:(DE-HGF)0$$aOrchard, Garrick$$b3
001038223 7001_ $$0P:(DE-Juel1)188273$$aNeftci, Emre$$b4$$ufzj
001038223 773__ $$a10.48550/ARXIV.2408.15800
001038223 909CO $$ooai:juser.fz-juelich.de:1038223$$pVDB
001038223 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188273$$aForschungszentrum Jülich$$b4$$kFZJ
001038223 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$$x0
001038223 9141_ $$y2024
001038223 920__ $$lyes
001038223 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001038223 980__ $$apreprint
001038223 980__ $$aVDB
001038223 980__ $$aI:(DE-Juel1)PGI-15-20210701
001038223 980__ $$aUNRESTRICTED