001025399 001__ 1025399
001025399 005__ 20250203103109.0
001025399 0247_ $$2doi$$a10.1109/IPDPSW59300.2023.00132
001025399 0247_ $$2WOS$$aWOS:001055030700095
001025399 037__ $$aFZJ-2024-02858
001025399 1001_ $$0P:(DE-HGF)0$$aBenmeziane, Hadjer$$b0$$eCorresponding author
001025399 1112_ $$aIEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)$$cSt. Petersburg$$d2023-05-15 - 2023-05-19$$wUSA
001025399 245__ $$aSkip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training
001025399 260__ $$bIEEE$$c2023
001025399 300__ $$a790-794
001025399 3367_ $$2ORCID$$aCONFERENCE_PAPER
001025399 3367_ $$033$$2EndNote$$aConference Paper
001025399 3367_ $$2BibTeX$$aINPROCEEDINGS
001025399 3367_ $$2DRIVER$$aconferenceObject
001025399 3367_ $$2DataCite$$aOutput Types/Conference Paper
001025399 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1732779967_8303
001025399 520__ $$aSpiking neural networks (SNNs) have gained attention as a promising alternative to traditional artificial neural networks (ANNs) due to their potential for energy efficiency and their ability to model spiking behavior in biological systems. However, the training of SNNs is still a challenging problem, and new techniques are needed to improve their performance. In this paper, we study the impact of skip connections on SNNs and propose a hyperparameter optimization technique that adapts models from ANN to SNN. We demonstrate that optimizing the position, type, and number of skip connections can significantly improve the accuracy and efficiency of SNNs by enabling faster convergence and increasing information flow through the network. Our results show an average +8% accuracy increase on CIFAR-10-DVS and DVS128 Gesture datasets adaptation of multiple state-of-the-art models.
001025399 536__ $$0G:(DE-HGF)POF4-5234$$a5234 - Emerging NC Architectures (POF4-523)$$cPOF4-523$$fPOF IV$$x0
001025399 536__ $$0G:(DE-82)BMBF-16ME0398K$$aBMBF 16ME0398K - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0398K)$$cBMBF-16ME0398K$$x1
001025399 536__ $$0G:(DE-82)BMBF-16ME0399$$aBMBF 16ME0399 - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0399)$$cBMBF-16ME0399$$x2
001025399 588__ $$aDataset connected to CrossRef Conference
001025399 7001_ $$0P:(DE-HGF)0$$aOunnoughene, Amine Ziad$$b1
001025399 7001_ $$0P:(DE-HGF)0$$aHamzaoui, Imane$$b2
001025399 7001_ $$0P:(DE-Juel1)176778$$aBouhadjar, Younes$$b3$$ufzj
001025399 773__ $$a10.1109/IPDPSW59300.2023.00132
001025399 8564_ $$uhttps://juser.fz-juelich.de/record/1025399/files/Skip_Connections_in_Spiking_Neural_Networks_An_Analysis_of_Their_Effect_on_Network_Training.pdf$$yRestricted
001025399 909CO $$ooai:juser.fz-juelich.de:1025399$$pVDB
001025399 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176778$$aForschungszentrum Jülich$$b3$$kFZJ
001025399 9131_ $$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
001025399 9141_ $$y2024
001025399 920__ $$lyes
001025399 9201_ $$0I:(DE-Juel1)PGI-15-20210701$$kPGI-15$$lNeuromorphic Software Eco System$$x0
001025399 9201_ $$0I:(DE-Juel1)PGI-7-20110106$$kPGI-7$$lElektronische Materialien$$x1
001025399 980__ $$acontrib
001025399 980__ $$aVDB
001025399 980__ $$aI:(DE-Juel1)PGI-15-20210701
001025399 980__ $$aI:(DE-Juel1)PGI-7-20110106
001025399 980__ $$aUNRESTRICTED