将脉冲神经网络与高维计算结合，实现低延迟、低功耗的高效解码。
Hyperdimensional Decoding of Spiking Neural Networks
- 用高维计算融合脉冲神经网络，提升解码效率。
- 在多个数据集上能耗降低1.24至3.67倍，延迟更低。
- 可识别未训练过的未知类别，适合实时低功耗场景。
本文提出一种新型脉冲神经网络（SNN）解码方法，将SNN与高维计算（HDC）结合，旨在实现高准确率、高抗噪性、低延迟和低能耗。相比现有解码方式，在多个文献中的测试案例中，该SNN-HDC模型均展现出更优的分类准确率、更低的分类延迟和更低的估算能耗。在DvsGesture数据集上，能耗降低1.24至3.67倍；在SL-Animals-DVS数据集上，降低1.38至2.27倍。该方法还能高效识别未训练过的未知类别，在DvsGesture数据集中对未见类别的样本识别率达100%。鉴于其多项优势，该解码方法为速率和时序解码提供了极具吸引力的替代方案。
原文摘要 · Abstract (English)
This work presents a novel spiking neural network (SNN) decoding method, combining SNNs with Hyperdimensional computing (HDC). The goal is to create a decoding method with high accuracy, high noise robustness, low latency and low energy usage. Compared to analogous architectures decoded with existing approaches, the presented SNN-HDC model attains generally better classification accuracy, lower classification latency and lower estimated energy consumption on multiple test cases from literature. The SNN-HDC achieved estimated energy consumption reductions ranging from 1.24x to 3.67x on the DvsGesture dataset and from 1.38x to 2.27x on the SL-Animals-DVS dataset. The presented decoding method can also efficiently identify unknown classes it has not been trained on. In the DvsGesture dataset the SNN-HDC model can identify 100% of samples from an unseen/untrained class. Given the numerous benefits shown and discussed in this paper, this decoding method represents a very compelling alternative to both rate and latency decoding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。