TY - JOUR
T1 - SpiKernel
T2 - A Kernel Size Exploration Methodology for Improving Accuracy of the Embedded Spiking Neural Network Systems
AU - Putra, Rachmad Vidya Wicaksana
AU - Shafique, Muhammad
N1 - Publisher Copyright:
© 2009-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - Spiking Neural Networks (SNNs) can offer ultra-low power/energy consumption for machine learning-based application tasks due to their sparse spike-based operations. Currently, most of the SNN architectures need a significantly larger model size to achieve higher accuracy, which is not suitable for resource-constrained embedded applications. Therefore, developing SNNs that can achieve high accuracy with acceptable memory footprint is highly needed. Toward this, we propose SpiKernel, a novel methodology that improves the accuracy of SNNs through kernel size exploration. Its key steps include (1) investigating the impact of different kernel sizes on the accuracy, (2) devising new sets of kernel sizes, (3) generating SNN architectures using neural architecture search based on the selected kernel sizes, and (4) analyzing the accuracy-memory trade-offs for SNN model selection. The experimental results show that our SpiKernel achieves higher accuracy than state-of-The-Art works (i.e., 93.24% for CIFAR10, 70.84% for CIFAR100, and 62% for TinyImageNet) with less than 10M parameters and up to 4.8x speed-up of searching time, thereby making it suitable for embedded applications.
AB - Spiking Neural Networks (SNNs) can offer ultra-low power/energy consumption for machine learning-based application tasks due to their sparse spike-based operations. Currently, most of the SNN architectures need a significantly larger model size to achieve higher accuracy, which is not suitable for resource-constrained embedded applications. Therefore, developing SNNs that can achieve high accuracy with acceptable memory footprint is highly needed. Toward this, we propose SpiKernel, a novel methodology that improves the accuracy of SNNs through kernel size exploration. Its key steps include (1) investigating the impact of different kernel sizes on the accuracy, (2) devising new sets of kernel sizes, (3) generating SNN architectures using neural architecture search based on the selected kernel sizes, and (4) analyzing the accuracy-memory trade-offs for SNN model selection. The experimental results show that our SpiKernel achieves higher accuracy than state-of-The-Art works (i.e., 93.24% for CIFAR10, 70.84% for CIFAR100, and 62% for TinyImageNet) with less than 10M parameters and up to 4.8x speed-up of searching time, thereby making it suitable for embedded applications.
KW - embedded applications
KW - kernel size exploration
KW - neural architecture search
KW - Spiking neural networks
UR - http://www.scopus.com/inward/record.url?scp=85211585751&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85211585751&partnerID=8YFLogxK
U2 - 10.1109/LES.2024.3510197
DO - 10.1109/LES.2024.3510197
M3 - Article
AN - SCOPUS:85211585751
SN - 1943-0663
JO - IEEE Embedded Systems Letters
JF - IEEE Embedded Systems Letters
ER -