Pith. sign in

REVIEW 1 cited by

Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.06582 v2 pith:6LQSYQ5Q submitted 2023-08-12 cs.NE

classification cs.NE
keywords codingattentionsnnsefficiencygatednetworksneuralaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Spiking neural networks (SNNs) are emerging as an energy-efficient alternative to traditional artificial neural networks (ANNs) due to their unique spike-based event-driven nature. Coding is crucial in SNNs as it converts external input stimuli into spatio-temporal feature sequences. However, most existing deep SNNs rely on direct coding that generates powerless spike representation and lacks the temporal dynamics inherent in human vision. Hence, we introduce Gated Attention Coding (GAC), a plug-and-play module that leverages the multi-dimensional gated attention unit to efficiently encode inputs into powerful representations before feeding them into the SNN architecture. GAC functions as a preprocessing layer that does not disrupt the spike-driven nature of the SNN, making it amenable to efficient neuromorphic hardware implementation with minimal modifications. Through an observer model theoretical analysis, we demonstrate GAC's attention mechanism improves temporal dynamics and coding efficiency. Experiments on CIFAR10/100 and ImageNet datasets demonstrate that GAC achieves state-of-the-art accuracy with remarkable efficiency. Notably, we improve top-1 accuracy by 3.10\% on CIFAR100 with only 6-time steps and 1.07\% on ImageNet while reducing energy usage to 66.9\% of the previous works. To our best knowledge, it is the first time to explore the attention-based dynamic coding scheme in deep SNNs, with exceptional effectiveness and efficiency on large-scale datasets.The Code is available at https://github.com/bollossom/GAC.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhanced Temporal Processing in Spiking Neural Networks for Static Object Detection Using 3D Convolutions

    cs.AI 2024-12 reject novelty 5.0 of 10

    A directly trained spiking YOLOv5n using 3D convolutions and a temporal recurrence mechanism reports mAP within 0.001 to 0.008 of a same-architecture ANN on COCO2017 and VOC at 224x224.

Pith tools