Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks. (arXiv:2308.04672v1 [cs.CV])

Brain-inspired Spiking Neural Networks (SNNs) have the characteristics of
event-driven and high energy-efficient, which are different from traditional
Artificial Neural Networks (ANNs) when deployed on edge devices such as
neuromorphic chips. Most previous work focuses on SNNs training strategies to
improve model performance and brings larger and deeper network architectures.
It is difficult to deploy these complex networks on resource-limited edge
devices directly. To meet such demand, people compress SNNs very cautiously to
balance the performance and the computation efficiency. …

anns artificial artificial neural networks arxiv brain brain-inspired chips compression devices edge edge devices energy event minimax networks neural networks neuromorphic neuromorphic chips optimization performance spiking neural networks strategies training work