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

Recent Spiking Neural Networks (SNNs) works focus on an image classificationtask, therefore various coding techniques have been proposed to convert animage into temporal binary spikes. Among them, rate coding and direct codingare regarded as prospective candidates for building a practical SNN system asthey show state-of-the-art performance on large-scale datasets. Despite theirusage, there is little attention to comparing these two coding schemes in afair manner. In this paper, we conduct a comprehensive analysis of the twocodings from three perspectives: accuracy, adversarial robustness, andenergy-efficiency. First, we compare the performance of two coding techniqueswith various architectures and datasets. Then, we measure the robustness of thecoding techniques on two adversarial attack methods. Finally, we compare theenergy-efficiency of two coding schemes on a digital hardware platform. Ourresults show that direct coding can achieve better accuracy especially for asmall number of timesteps. In contrast, rate coding shows better robustness toadversarial attacks owing to the non-differentiable spike generation process.Rate coding also yields higher energy-efficiency than direct coding whichrequires multi-bit precision for the first layer. Our study explores thecharacteristics of two codings, which is an important design consideration forbuilding SNNs. The code is made available athttps://github.com/Intelligent-Computing-Lab-Yale/Rate-vs-Direct.

Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?