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 3:

Comparison of the Training and Validation Errors of Different Algorithms for Three-Hidden Layer NNs on the MNIST Data Set.

Algorithm Learning Rate Training Error (%) Validation Error (%) Number of Epochs
EP: ±β αW=0.128, 0.032, 0.008, 0.002 0 2.73 250
EP: +β αW =0.128, 0.032, 0.008, 0.002 0 2.77 250
EP lateral αW=0.128, 0.032, 0.008, 0.002;
αL = 0.192, 0.048, 0.012		 0 2.4 250
CSM αW =0.5, 0.375, 0.281, 0.211;
αL =0.75, 0.562, 0.422		 0 4.82 250
CSM Adaptive αW =0.5, 0.375, 0.281, 0.211;
αL =0.75, 0.562, 0.422		 0 3.52 250