Contribution to a conference proceedings

FZJ-2024-02858

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Skip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training

Benmeziane, H. (Corresponding author) ; Ounnoughene, A. Z. ; Hamzaoui, I. ; Bouhadjar, Y.FZJ*

2023
IEEE

This record in other databases:  

Please use a persistent id in citations: doi:10.1109/IPDPSW59300.2023.00132

Abstract: 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.

---

Contributing Institute(s):

1. Neuromorphic Software Eco System (PGI-15)
2. Elektronische Materialien (PGI-7)

Research Program(s):

1. 5234 - Emerging NC Architectures (POF4-523) (POF4-523)
2. BMBF 16ME0398K - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0398K) (BMBF-16ME0398K)
3. BMBF 16ME0399 - Verbundprojekt: Neuro-inspirierte Technologien der künstlichen Intelligenz für die Elektronik der Zukunft - NEUROTEC II - (BMBF-16ME0399) (BMBF-16ME0399)

Appears in the scientific report 2024

---