Home > Publications database > Skip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training > print

001     1025399
005     20250203103109.0
024 7 _ |a 10.1109/IPDPSW59300.2023.00132
|2 doi
024 7 _ |a WOS:001055030700095
|2 WOS
037 _ _ |a FZJ-2024-02858
100 1 _ |a Benmeziane, Hadjer
|0 P:(DE-HGF)0
|b 0
|e Corresponding author
111 2 _ |a IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
|c St. Petersburg
|d 2023-05-15 - 2023-05-19
|w USA
245 _ _ |a Skip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training
260 _ _ |c 2023
|b IEEE
300 _ _ |a 790-794
336 7 _ |a CONFERENCE_PAPER
|2 ORCID
336 7 _ |a Conference Paper
|0 33
|2 EndNote
336 7 _ |a INPROCEEDINGS
|2 BibTeX
336 7 _ |a conferenceObject
|2 DRIVER
336 7 _ |a Output Types/Conference Paper
|2 DataCite
336 7 _ |a Contribution to a conference proceedings
|b contrib
|m contrib
|0 PUB:(DE-HGF)8
|s 1732779967_8303
|2 PUB:(DE-HGF)
520 _ _ |a Spiking 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.
536 _ _ |a 5234 - Emerging NC Architectures (POF4-523)
|0 G:(DE-HGF)POF4-5234
|c POF4-523
|f POF IV
|x 0
536 _ _ |a BMBF 16ME0398K - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0398K)
|0 G:(DE-82)BMBF-16ME0398K
|c BMBF-16ME0398K
|x 1
536 _ _ |a BMBF 16ME0399 - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0399)
|0 G:(DE-82)BMBF-16ME0399
|c BMBF-16ME0399
|x 2
588 _ _ |a Dataset connected to CrossRef Conference
700 1 _ |a Ounnoughene, Amine Ziad
|0 P:(DE-HGF)0
|b 1
700 1 _ |a Hamzaoui, Imane
|0 P:(DE-HGF)0
|b 2
700 1 _ |a Bouhadjar, Younes
|0 P:(DE-Juel1)176778
|b 3
|u fzj
773 _ _ |a 10.1109/IPDPSW59300.2023.00132
856 4 _ |u https://juser.fz-juelich.de/record/1025399/files/Skip_Connections_in_Spiking_Neural_Networks_An_Analysis_of_Their_Effect_on_Network_Training.pdf
|y Restricted
909 C O |o oai:juser.fz-juelich.de:1025399
|p VDB
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 3
|6 P:(DE-Juel1)176778
913 1 _ |a DE-HGF
|b Key Technologies
|l Natural, Artificial and Cognitive Information Processing
|1 G:(DE-HGF)POF4-520
|0 G:(DE-HGF)POF4-523
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-500
|4 G:(DE-HGF)POF
|v Neuromorphic Computing and Network Dynamics
|9 G:(DE-HGF)POF4-5234
|x 0
914 1 _ |y 2024
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)PGI-15-20210701
|k PGI-15
|l Neuromorphic Software Eco System
|x 0
920 1 _ |0 I:(DE-Juel1)PGI-7-20110106
|k PGI-7
|l Elektronische Materialien
|x 1
980 _ _ |a contrib
980 _ _ |a VDB
980 _ _ |a I:(DE-Juel1)PGI-15-20210701
980 _ _ |a I:(DE-Juel1)PGI-7-20110106
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21