Skip to main content

Table 3 Main Features of Semeion Machine Learning Systems employed in the study

From: Development of machine learning models to predict RT-PCR results for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in patients with influenza-like symptoms using only basic clinical data

ANNs Architecture Hidden layers Learning Rate Epochs Initialization Output Function Nickname
Conic Net [31] 5 Layers=
4x12x12x12
0.01 1000 Auto-encoders Soft Max D_FF_Conic (4x12x12x12)
  5 Layers=
6x12x12x12
0.01 1000 Auto-encoders Soft Max D_FF_Conic (6x12x12x12)
Sine Net [32,33,34] 1 Layer = 48 0.1 2000 Random Soft Max D_FF_Sn [35]
Back Propagation [29] 0 Layer = L 0.1 1000 Random Soft Max D_FF_Bp (0)
  1 Layer = 24 0.1 1000 Random Soft Max D_FF_Bp
[22]
  5 Layers=
16x16x16x16
0.01 2000 Auto-encoders Soft Max D_FF_Bp
(16x16x16x16)
Bi-Modal Net 1 Layer = 48 0.1 1000 Random Soft Max D_FF_Bm
[35]
Gauss Net [36] 1 Layer = 64 0.01 1000 Random Soft Max D_FF_GNet
[37]