Return to search

Low-bit Quantization-aware Training of Spiking Neural Networks

Deep neural networks are proven to be highly effective tools in various domains, yet their computational and memory costs restrict them from being widely deployed on portable devices. The recent rapid increase of edge computing devices has led to an active search for techniques to address the above-mentioned limitations of machine learning frameworks. The quantization of artificial neural networks (ANNs), which converts the full-precision synaptic weights into low-bit versions, emerged as one of the solutions. At the same time, spiking neural networks (SNNs) have become an attractive alternative to conventional ANNs due to their temporal information processing capability, energy efficiency, and high biological plausibility. Despite being driven by the same motivation, the simultaneous utilization of both concepts has not been fully studied.

Therefore, this thesis work aims to bridge the gap between recent progress in quantized neural networks and SNNs. It presents an extensive study on the performance of the quantization function, represented as a linear combination of sigmoid functions, exploited in low-bit weight quantization in SNNs. The given quantization function demonstrates the state-of-the-art performance on four popular benchmarks, CIFAR10-DVS, DVS128 Gesture, N-Caltech101, and N-MNIST, for binary networks (64.05%, 95.45%, 68.71%, and 99.365 respectively) with small accuracy drops (8.03%, 1.18%, 3.47%, and 0.17% respectively) and up to 32x memory savings, which outperforms the existing methods.

Identiferoai:union.ndltd.org:kaust.edu.sa/oai:repository.kaust.edu.sa:10754/676589
Date04 1900
CreatorsShymyrbay, Ayan
ContributorsEltawil, Ahmed, Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division, Salama, Khaled N., Fahmy, Suhaib A.
Source SetsKing Abdullah University of Science and Technology
LanguageEnglish
Detected LanguageEnglish
TypeThesis
Rights2023-04-27, At the time of archiving, the student author of this thesis opted to temporarily restrict access to it. The full text of this thesis became available to the public after the expiration of the embargo on 2023-04-27.

Page generated in 0.002 seconds