Skip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training

Hadjer Benmeziane, Amine Ziad Ounnoughene, Imane Hamzaoui, Younes Bouhadjar
3/23/2023
cs.NEcs.CVcs.LG

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Towards Efficient and Accurate Spiking Neural Networks via Adaptive Bit Allocation

84% match1 repo12025

Co-learning synaptic delays, weights and adaptation in spiking neural networks

84% match2023

Learning Spiking Neural Network from Easy to Hard task

84% match2023

On Reducing Activity with Distillation and Regularization for Energy Efficient Spiking Neural Networks

84% match2024

High-performance deep spiking neural networks with 0.3 spikes per neuron

84% match2023

Training a General Spiking Neural Network with Improved Efficiency and Minimum Latency

83% match1 repo42024

Cite this paper

@article{benmeziane2023skip,
  title  = {Skip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training},
  author = {Hadjer Benmeziane and Amine Ziad Ounnoughene and Imane Hamzaoui and Younes Bouhadjar},
  year   = {2023},
  eprint = {2303.13563},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.13563v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.13563.svg)](https://codeofpaper.com/paper/2303.13563)

Discussion