.png){kind=icon}
返回
mlGeNN: accelerating SNN inference using GPU-enabled neural networks
.png){kind=icon}
OA
AI
DOI：10.1088/2634-4386/ac5ac5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper we present mlGeNN-a Python library for the conversion of artificial neural networks (ANNs) specified in Keras to spiking neural networks (SNNs). SNNs are simulated using GeNN with extensions to efficiently support convolutional connectivity and batching. We evaluate converted SNNs on CIFAR-10 and ImageNet classification tasks and compare the performance to both the original ANNs and other SNN simulators. We find that performing inference using a VGG-16 model, trained on the CIFAR-10 dataset, is 2.5x faster than BindsNet and, when using a ResNet-20 model trained on CIFAR-10 with FewSpike ANN to SNN conversion, mlGeNN is only a little over 2x slower than TensorFlow.
Keyword:
machine learning
spiking neural networks
GPU
ANN to SNN conversion
convolutional neural networks
GeNN
ResNet
期刊
IF:
6.1
论文数:
340
被引数:
920
机构
引用论文
Event-based backpropagation can compute exact gradients for spiking neural networks基于事件的反向传播可以为尖峰神经网络计算精确的梯度.png)
SCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏Contributions of evacuation proctography and anorectal manometry to evaluation of adults with constipation and defecatory difficulty排空直肠造影和肛门直肠测压对成人便秘和排便困难的评估的贡献
PREAI
分享收藏
查看更多内容