Skip to Main Content
Table 7:
Comparison of the error rates (%), the computational times, and the average numbers of epochs for network training, on the CIFAR-10 dataset with the different parameter N. We run each method ten times and report the errors in the format of “best (mean ± std).” The values of the computational time and the average number of epochs are the mean over the ten runs.
MethodError rateTime (days)Average # epochs
CGP-CNN (ConvSet) 5.92(6.48±0.48) 15.6 50.0 
with early termination (N=35.61(6.52±0.59) 3.32 8.97 
with early termination (N=55.81(6.34±0.39) 6.73 18.8 
with early termination (N=106.40(6.93±0.50) 11.4 30.6 
CGP-CNN (ResSet) 5.01(6.10±0.89) 14.7 50.0 
with early termination (N=35.30(6.22±0.46) 2.39 7.96 
with early termination (N=55.42(6.34±0.61) 4.93 15.1 
with early termination (N=105.27(6.12±0.50) 6.05 23.9 
CGP-CNN (ResSet) with RichInit 4.90(5.60±0.52) 11.7 50.0 
with early termination (N=35.06(5.83±0.47) 1.29 6.88 
with early termination (N=55.07(5.76±0.57) 2.86 12.4 
with early termination (N=104.90(5.54±0.60) 6.36 22.2 
MethodError rateTime (days)Average # epochs
CGP-CNN (ConvSet) 5.92(6.48±0.48) 15.6 50.0 
with early termination (N=35.61(6.52±0.59) 3.32 8.97 
with early termination (N=55.81(6.34±0.39) 6.73 18.8 
with early termination (N=106.40(6.93±0.50) 11.4 30.6 
CGP-CNN (ResSet) 5.01(6.10±0.89) 14.7 50.0 
with early termination (N=35.30(6.22±0.46) 2.39 7.96 
with early termination (N=55.42(6.34±0.61) 4.93 15.1 
with early termination (N=105.27(6.12±0.50) 6.05 23.9 
CGP-CNN (ResSet) with RichInit 4.90(5.60±0.52) 11.7 50.0 
with early termination (N=35.06(5.83±0.47) 1.29 6.88 
with early termination (N=55.07(5.76±0.57) 2.86 12.4 
with early termination (N=104.90(5.54±0.60) 6.36 22.2 
Close Modal

or Create an Account

Close Modal
Close Modal