期刊
ELECTRONICS LETTERS
卷 53, 期 20, 页码 1347-1348出版社
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/el.2017.2219
关键词
neural nets; object recognition; real-time recognition tasks; CIFAR10; MNIST; spiking neurons; convolutional layers; pooling function; retraining; layer-wise quantisation method; DNN; deep neural network; SNN; low-inference-latency spiking neural networks; pooling method
Spiking neural network (SNN) that converted from conventional deep neural network (DNN) has shown great potential as a solution for fast and efficient recognition. A layer-wise quantisation method based on retraining is proposed to quantise the activation of DNN, which reduces the number of time steps required by converted SNN to achieve minimal accuracy loss. Pooling function is incorporated into convolutional layers to reduce at most 20% of spiking neurons. The converted SNNs achieved 99.15% accuracy on MNIST and 82.9% on CIFAR10 by only seven time steps, and only 10-40% of spikes need to be processed compared with networks using traditional algorithms. The experimental results show that the proposed methods are able to build hardware-friendly SNNs with ultra-low-inference latency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据