Attention Spiking Neural Networks

Внимательные импульсные нейронные сети
Yonghong Tian, Yifan Hu, Guoqi Li, Lei Deng, Bo Xu, Guangshe Zhao, Man Yao, Hengyu Zhang
2023-01-31

ImageNet-1Kblock dynamical isometryevent-based action recognitionmulti-dimensional attentionspiking neural networks
Brain-inspired spiking neural networks (SNNs) are becoming a promising energy-efficient alternative to traditional artificial neural networks (ANNs). However, the performance gap between SNNs and ANNs has been a significant hindrance to deploying SNNs ubiquitously. To leverage the full potential of SNNs, in this paper we study the attention mechanisms, which can help human focus on important information. We present our idea of attention in SNNs with a multi-dimensional attention module, which infers attention weights along the temporal, channel, as well as spatial dimension separately or simultaneously. Based on the existing neuroscience theories, we exploit the attention weights to optimize membrane potentials, which in turn regulate the spiking response. Extensive experimental results on event-based action recognition and image classification datasets demonstrate that attention facilitates vanilla SNNs to achieve sparser spiking firing, better performance, and energy efficiency concurrently. In particular, we achieve top-1 accuracy of 75.92% and 77.08% on ImageNet-1 K with single/4-step Res-SNN-104, which are state-of-the-art results in SNNs. Compared with counterpart Res-ANN-104, the performance gap becomes -0.95/+0.21 percent and the energy efficiency is 31.8×/7.4×. To analyze the effectiveness of attention SNNs, we theoretically prove that the spiking degradation or the gradient vanishing, which usually holds in general SNNs, can be resolved by introducing the block dynamical isometry theory. We also analyze the efficiency of attention SNNs based on our proposed spiking response visualization method. Our work lights up SNN's potential as a general backbone to support various applications in the field of SNN research, with a great balance between effectiveness and energy efficiency.
1
Attention weights optimize membrane potentials and regulate spiking responses, enabling vanilla SNNs to achieve sparser firing, higher accuracy, and improved energy efficiency simultaneously.
2
Compared with Res-ANN-104, the performance gaps are -0.95 and +0.21 percentage points, while energy efficiency reaches 31.8× and 7.4× for single-step and four-step models.
3
On ImageNet-1K, single-step and four-step Res-SNN-104 achieve top-1 accuracies of 75.92% and 77.08%, respectively, reported as state-of-the-art SNN results.
4
The paper introduces a multidimensional attention module for SNNs that separately or jointly models temporal, channel, and spatial attention.
5
Theoretical analysis shows that block dynamical isometry can resolve spiking degradation or gradient vanishing commonly encountered in SNNs; a spiking-response visualization method further analyzes efficiency.

spiking neural networks (SNNs)

the effects of multi-dimensional attention mechanisms on SNN spiking responses, accuracy, sparsity, energy efficiency, and training dynamics

Publication Details
Publication Date
2023-01-31
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Yonghong Tian
Yifan Hu
Guoqi Li
Lei Deng
Bo Xu
Guangshe Zhao
Man Yao
Hengyu Zhang
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%