Bimodal accuracy distribution in quantisation aware training of SNNs: an investigation

Durai Arun Pannir Selvam; Alan Wilmshurst; Kevin Thomas; Gaetano Di Caterina

doi:10.1117/12.3033999

13 November 2024 Bimodal accuracy distribution in quantisation aware training of SNNs: an investigation

Durai Arun Pannir Selvam, Alan Wilmshurst, Kevin Thomas, Gaetano Di Caterina

Proceedings Volume 13206, Artificial Intelligence for Security and Defence Applications II; 132060E (2024) https://doi.org/10.1117/12.3033999
Event: Security + Defence, 2024, Edinburgh, United Kingdom

Abstract

Understanding the caveats of deploying a Spiking Neural Networks (SNNs) in an embedded system is important, due to their potential to achieve high efficiency in applications using event-based data. This work investigates the effects of the quantisation of SNNs from the perspective of deploying a model onto FPGAs. Three SNN models were trained using Quantisation-aware training (QAT). In addition, three different types of quantisation were applied on all three models. Further, these models are trained while they are represented through various custom bit-depths using Brevitas. Then, the performance metric curves such as accuracy, training loss, and test loss resulted from QAT were viewed as performance distribution, to show that the significant accuracy drop found in these curves manifests itself as a bi-modal distribution This work then investigates whether the decrease in accuracy is consistent across different models.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Durai Arun Pannir Selvam, Alan Wilmshurst, Kevin Thomas, and Gaetano Di Caterina "Bimodal accuracy distribution in quantisation aware training of SNNs: an investigation", Proc. SPIE 13206, Artificial Intelligence for Security and Defence Applications II, 132060E (13 November 2024); https://doi.org/10.1117/12.3033999

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available