Skip to Main Content
Table 8:
Comparison of the error rates on the CIFAR-10 dataset (small-data scenario). We run the experiment ten times and report the classification errors in the format of “best (mean ± std).” The numbers of learnable weight parameters of the best architecture are also reported.
ModelError rate# params
VGG (Simonyan and Zisserman, 2015) 23.05(24.07±0.43) 15.2M 
ResNet (He et al., 2016) 24.01(24.83±0.51) 1.70M 
CGP-CNN (ConvSet) 19.78(22.14±1.80) 1.94M 
CGP-CNN (ResSet) 19.33(20.52±1.36) 0.92M 
ModelError rate# params
VGG (Simonyan and Zisserman, 2015) 23.05(24.07±0.43) 15.2M 
ResNet (He et al., 2016) 24.01(24.83±0.51) 1.70M 
CGP-CNN (ConvSet) 19.78(22.14±1.80) 1.94M 
CGP-CNN (ResSet) 19.33(20.52±1.36) 0.92M 
Close Modal

or Create an Account

Close Modal
Close Modal