Table 9.

Inference #time-steps and corresponding speedup comparison between SNN and ANN-SNN converted networks for benchmark datasets trained on different network models.

Dataset	Model	Timesteps			SNN Inference Speedup 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	50	180	200	3.6x	4x
				500		10x
SVHN	VGG7	100	500	1,600	5x	16x
			2,500	2,600	25x	26x
	ResNet7	100	500	400	5x	4x
			3,000	2,500	30x	25x
CIFAR-10	VGG9	100	500	800	5x	8x
			2,500	3,600	25x	36x
	ResNet9	100	800	600	8x	6x
			3,000	3,000	30x	30x
	ResNet11	100	3500	600	35x	6x
				3,000		30x

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