001038217 001__ 1038217
001038217 005__ 20250203103320.0
001038217 0247_ $$2doi$$a10.48550/ARXIV.2411.04760
001038217 037__ $$aFZJ-2025-01253
001038217 1001_ $$0P:(DE-HGF)0$$aKarilanova, Sanja$$b0
001038217 245__ $$aZero-Shot Temporal Resolution Domain Adaptation for Spiking Neural Networks
001038217 260__ $$barXiv$$c2024
001038217 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1738076362_32538
001038217 3367_ $$2ORCID$$aWORKING_PAPER
001038217 3367_ $$028$$2EndNote$$aElectronic Article
001038217 3367_ $$2DRIVER$$apreprint
001038217 3367_ $$2BibTeX$$aARTICLE
001038217 3367_ $$2DataCite$$aOutput Types/Working Paper
001038217 520__ $$aSpiking Neural Networks (SNNs) are biologically-inspired deep neural networks that efficiently extract temporal information while offering promising gains in terms of energy efficiency and latency when deployed on neuromorphic devices. However, SNN model parameters are sensitive to temporal resolution, leading to significant performance drops when the temporal resolution of target data at the edge is not the same with that of the pre-deployment source data used for training, especially when fine-tuning is not possible at the edge. To address this challenge, we propose three novel domain adaptation methods for adapting neuron parameters to account for the change in time resolution without re-training on target time-resolution. The proposed methods are based on a mapping between neuron dynamics in SNNs and State Space Models (SSMs); and are applicable to general neuron models. We evaluate the proposed methods under spatio-temporal data tasks, namely the audio keyword spotting datasets SHD and MSWC as well as the image classification NMINST dataset. Our methods provide an alternative to - and in majority of the cases significantly outperform - the existing reference method that simply scales the time constant. Moreover, our results show that high accuracy on high temporal resolution data can be obtained by time efficient training on lower temporal resolution data and model adaptation.
001038217 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001038217 588__ $$aDataset connected to DataCite
001038217 650_7 $$2Other$$aMachine Learning (cs.LG)
001038217 650_7 $$2Other$$aFOS: Computer and information sciences
001038217 7001_ $$0P:(DE-Juel1)201205$$aFabre, Maxime$$b1$$ufzj
001038217 7001_ $$0P:(DE-Juel1)188273$$aNeftci, Emre$$b2$$ufzj
001038217 7001_ $$0P:(DE-HGF)0$$aÖzçelikkale, Ayça$$b3
001038217 773__ $$a10.48550/ARXIV.2411.04760
001038217 909CO $$ooai:juser.fz-juelich.de:1038217$$pVDB
001038217 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)201205$$aForschungszentrum Jülich$$b1$$kFZJ
001038217 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188273$$aForschungszentrum Jülich$$b2$$kFZJ
001038217 9131_ $$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
001038217 9141_ $$y2024
001038217 920__ $$lyes
001038217 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001038217 980__ $$apreprint
001038217 980__ $$aVDB
001038217 980__ $$aI:(DE-Juel1)PGI-15-20210701
001038217 980__ $$aUNRESTRICTED