. 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 2:

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

Algorithm	Learning Rate	Training Error (%)	Validation Error (%)	Number of Epochs
EP: ±β	α_W = 0.1, 0.05	0	2.53	40
EP: +β	α_W = 0.5, 0.125	0.034	2.18	100
EP: lateral	α_W = 0.5, 0.25, α_L = 0.75	0	2.29	25
CSM	α_W = 0.5, 0.375, α_L = 0.01	0	2.16	25