Skip to main content
. 2023 Feb 16;33:100443. doi: 10.1016/j.jii.2023.100443

Table 1.

The hyper-parameters in the ResNet.

Symbol Description Value
K Kernel matrix 3×3
p Number of kernels in convolutional layers 32
b Mini-batch size 10
η0 Initial value of learning rate 0.001
υ The decay rate of learning rate 0.0002
f0 Initial value of the first-order moment 0
s0 Initial value of the second-order moment 0
ϵ1 The exponential decay rate of the first-order moment estimation 0.9
ϵ2 The exponential decay rate of the second-order moment estimation 0.999
δ A minimum value close to zero 107