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

Figure 7.

Figure 7

Accuracy improvement with network depth for (A) SVHN dataset and (B) CIFAR-10 dataset. In (A), inference accuracy improves with an increase in network depth. In (B), the non-residual networks saturate at a certain depth and start to degrade if network depth increases further. However, the residual blocks in deep residual ANNs allow the network to maintain peak classification accuracy (ResNet9 and ResNet11).