English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Spiking Neural Networks (SNNs) have attracted great attention due to theirdistinctive characteristics of low power consumption and temporal informationprocessing. ANN-SNN conversion, as the most commonly used training method forapplying SNNs, can ensure that converted SNNs achieve comparable performance toANNs on large-scale datasets. However, the performance degrades severely underlow quantities of time-steps, which hampers the practical applications of SNNsto neuromorphic chips. In this paper, instead of evaluating differentconversion errors and then eliminating these errors, we define an offset spiketo measure the degree of deviation between actual and desired SNN firing rates.We perform a detailed analysis of offset spike and note that the firing of oneadditional (or one less) spike is the main cause of conversion errors. Based onthis, we propose an optimization strategy based on shifting the initialmembrane potential and we theoretically prove the corresponding optimalshifting distance for calibrating the spike. In addition, we also note that ourmethod has a unique iterative property that enables further reduction ofconversion errors. The experimental results show that our proposed methodachieves state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNetdatasets. For example, we reach a top-1 accuracy of 67.12% on ImageNet whenusing 6 time-steps. To the best of our knowledge, this is the first time anANN-SNN conversion has been shown to simultaneously achieve high accuracy andultralow latency on complex datasets. Code is available athttps://github.com/hzc1208/ANN2SNN_COS.

Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes