← Back to all news
arXiv Machine Learning By Rajshekhar Rakshit, Devgokul B. V, Rakshitha Kalkura, Gopalakrishnan Srinivasan

Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications

Read the original on arXiv Machine Learning →

The paper introduces a spike‑aware, gradient‑based mixed‑precision quantization framework for Spiking Neural Networks (SNNs), which assigns bit‑widths adaptively using first‑order gradient information. This approach avoids the memory and computational overhead of Hessian‑based methods like HAWQ‑V2 and is evaluated on VGG, ResNet, and Vision Transformer architectures across CIFAR‑10/100, ImageNet, and DVS‑CIFAR‑10 datasets. On ResNet‑34 with ImageNet, the method attains 73.30% accuracy at 4.78× compression, matching HAWQ‑V2 while reducing memory usage by 2.31× and bit‑allocation runtime by 100×, and it demonstrates energy‑efficient deployment without performance loss.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 19

SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks

SpikeQ introduces a spike‑guided post‑training quantization framework for spiking neural networks, selecting weight levels by simulating downstream neurons to minimize spike errors and designing a reset‑aware grid for pre‑fire membrane potential quantization that avoids spike flips. The method outperforms existing grids on seven image‑processing benchmarks, maintaining full‑precision accuracy with 2‑bit pre‑fire potentials and staying within 2.59 points of full precision at 4 bits while drastically reducing memory and energy usage.

By Kai Sun, Peibo Duan, Zhanglu Yan, Guowei Zhang, Yongsheng Huang, Levin Kuhlmann
computer-visionefficiencybenchmarks
More like this →
arXiv AI
Jul 15

Burst Spiking Neural Networks

arXiv:2607. 11914v1 Announce Type: cross Abstract: A central goal of current Spiking Neural Network (SNN) research is to improve their accuracy toward becoming low-power alternatives to Artificial Neural Networks (ANNs).

By Jiahong Zhang, Sijun Shen, Man Yao, Han Xu, Mingqiang Huang, Yonghong Tian, Bo Xu, Guoqi Li
efficiencybenchmarks
More like this →