Skip to main content
. Author manuscript; available in PMC: 2021 Nov 17.
Published in final edited form as: Neural Comput. 2021 Apr 13;33(5):1300–1328. doi: 10.1162/neco_a_01374

Table 5:

Comparison of the Validation Errors of Different Algorithms for Different Networks on the CIFAR-10 Data Set.

Algorithm, Connectivity, Number of Hidden Layers Learning Rate Training Error (%) Validation Error (%) Number of Errors
CSM, FC, 1HL αW = 0.059, 0.017
αL = 0.067		 1.77 59.21 ± 0.08 1000
CSM, FC, 2HL αW = 0.018, 7.51 × 10−4, 3.07 × 10−5
αL = 0.063, 2.59 × 10−3 		17.96 51.76 ± 0.002 3584
CSM, Str, 1HL αW = 0.050, 0.0375
αL = 0.01		 34 ± 3.7 49.5 ± 0.7 250
CSM, Str, 2HL αW = 0.265, 0.073, 0.020
αL = 0.075, 0.020		 46.8 ± 0.6 51.4 ± 0.7 200
EP, FC, 1HL αW = 0.014, 0.011 0.76 57.60 ± 0.06 1000
EP, FC, 2HL αW = 0.014, 0.011, 1.25 1.25 53.43 ± 0.04 1000