Skip to main content

Table 4 Comparisons of the mean and std of MSE between AE and CSDAE

From: Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder

  Noise factor Train data MSE (mean ± std) Test data MSE (mean ± std) Test noised data MSE (mean ± std)
AE 0.01 0.000983 ± 0.000304 0.001088 ± 0.0004 0.001112 ± 0.000405
CSDAE 0.01 0.000829 ± 0.000282 0.000923 ± 0.000369 0.000922 ± 0.000368
AE 0.05 0.001039 ± 0.000334 0.001146 ± 0.000427 0.001255 ± 0.000445
CSDAE 0.05 0.001003 ± 0.000334 0.001103 ± 0.000421 0.001174 ± 0.00045