Skip to main content
. 2016 Nov 8;10:508. doi: 10.3389/fnins.2016.00508

Table 3.

Comparison of accuracy of spiking CNN models on MNIST benchmark.

Network Preprocessing Ensemble Test accuracy (%)
CNN (Garbin et al., 2014) None 1 98.3
CNN (Diehl et al., 2015) None 1 99.1
Sparsely connected network (Esser et al., 2015) Affine transformation 64 99.42
CNN (This work) Elastic distortion 1 99.31