Skip to main content
. 2020 Feb 28;14:119. doi: 10.3389/fnins.2020.00119

Table 8.

#Spikes/Image inference and spike efficiency comparison between SNN and ANN-SNN converted networks for benchmark datasets trained on different network models.

Dataset Model Spike/Image Spike efficiency compared to
SNN ANN-SNN ANN-SNN ANN-SNN ANN-SNN
(Diehl et al., 2015) (Sengupta et al., 2019) (Diehl et al., 2015) (Sengupta et al., 2019)
MNIST LeNet 5.52E+04 3.4E+04 2.9E+04 0.62x 0.53x
7.3E+04 1.32x
SVHN VGG7 5.56E+06 3.7E+06 1.0E+07 0.67x 1.84x
1.9E+07 1.7E+07 3.40x 2.99x
ResNet7 4.66E+06 3.9E+06 3.1E+06 0.85x 0.67x
2.4E+07 2.0E+07 5.19x 4.30x
CIFAR-10 VGG9 1.24E+06 1.6E+06 2.2E+06 1.32x 1.80x
8.3E+06 9.6E+06 6.68x 7.78x
ResNet9 4.32E+06 2.7E+06 1.5E+06 0.63x 0.35x
1.0E+07 7.8E+06 2.39x 1.80x
ResNet11 1.53E+06 9.7E+06 1.8E+06 6.33x 1.17x
9.2E+06 5.99x

(For each network, the 1st row corresponds to iso-accuracy and the 2nd row corresponds to maximum-accuracy condition).