001038063 001__ 1038063
001038063 005__ 20250804115236.0
001038063 0247_ $$2doi$$a10.1109/ICONS62911.2024.00064
001038063 0247_ $$2WOS$$aWOS:001462433900056
001038063 037__ $$aFZJ-2025-01112
001038063 1001_ $$0P:(DE-HGF)0$$aBoeshertz, Gauthier$$b0$$eFirst author
001038063 1112_ $$a2024 International Conference on Neuromorphic Systems (ICONS)$$cArlington$$d2024-07-30 - 2024-08-02$$wVA
001038063 245__ $$aAccurate Mapping of RNNs on Neuromorphic Hardware with Adaptive Spiking Neurons
001038063 260__ $$bIEEE$$c2024
001038063 300__ $$a376-380
001038063 3367_ $$2ORCID$$aCONFERENCE_PAPER
001038063 3367_ $$033$$2EndNote$$aConference Paper
001038063 3367_ $$2BibTeX$$aINPROCEEDINGS
001038063 3367_ $$2DRIVER$$aconferenceObject
001038063 3367_ $$2DataCite$$aOutput Types/Conference Paper
001038063 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1738249404_31384
001038063 520__ $$aThanks to their parallel and sparse activity features, recurrent neural networks (RNNs) are well-suited for hardware implementation in low-power neuromorphic hardware. However, mapping rate-based RNNs to hardware-compatible spiking neural networks (SNNs) remains challenging. Here, we present a ΣΔ−low-pass RNN (lpRNN): an RNN architecture employing an adaptive spiking neuron model that encodes signals using ΣΔ-modulation and enables precise mapping. The ΣΔ-neuron communicates graded values using spike timing, and the dynamics of the IpRNN are set to match typical timescales for processing natural signals, such as speech. Our approach integrates rate and temporal coding, offering a robust solution for efficient and accurate conversion of RNNs to SNNs. We demonstrate the implementation of the IpRNN on Intel's neuromorphic research chip Loihi, achieving state-of-the-art classification results on audio benchmarks using 3-bit weights. These results call for a deeper investigation of recurrency and adaptation in event-based systems, which may lead to insights for edge computing applications where power-efficient real-time inference is required.
001038063 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001038063 588__ $$aDataset connected to CrossRef Conference
001038063 7001_ $$0P:(DE-HGF)0$$aIndiveri, Giacomo$$b1
001038063 7001_ $$0P:(DE-HGF)0$$aNair, Manu$$b2
001038063 7001_ $$0P:(DE-Juel1)201426$$aRenner, Alpha$$b3$$eCorresponding author
001038063 773__ $$a10.1109/ICONS62911.2024.00064
001038063 8564_ $$uhttps://doi.org/10.1109/ICONS62911.2024.00064
001038063 909CO $$ooai:juser.fz-juelich.de:1038063$$pVDB
001038063 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)201426$$aForschungszentrum Jülich$$b3$$kFZJ
001038063 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$$x0
001038063 9141_ $$y2024
001038063 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001038063 980__ $$acontrib
001038063 980__ $$aVDB
001038063 980__ $$aI:(DE-Juel1)PGI-15-20210701
001038063 980__ $$aUNRESTRICTED