Bi-modal accuracy distribution in quantisation aware training of SNNs: an investigation

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. This paper attempts to identify whether the decrease in accuracy is consistent across different models. 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.