Table 12 Results of the effect of different transfer functions between 2 layers in predicting compressive strength of 7 and 28 days of self-compacting concrete.

From: Predicting the compressive strength of self-compacting concrete by developed African vulture optimization algorithm-Elman neural networks

 

Transfer functions

Tansig–Tansig

Tansig–logsig

Tansig- purline

Purline–logsig

Purline–purline

Purline–Tansig

logsig–logsig

logsig–purline

logsig–tansig

MSE Test

\({F}_{c}7\)

51.21

153.01

56..10

208.87

59.66

59.24

144.40

45.95

51.35

\({F}_{c}28\)

66.34

371.56

105.57

295.56

208.87

208.36

371.56

62.91

76.98

MSE Train

\({F}_{c}7\)

35.75

128.96

55.60

172.58

87.49

95.51

123.49

63.76

71.81

\({F}_{c}28\)

47..89

339.25

105.89

290.90

218.45

222.38

339.25

59.38

56.99

R Test

\({F}_{c}7\)

0.84

0.67

0.83

−0.16

0.87

0.83

0.75

0.87

0.86

\({F}_{c}28\)

0.90

−0.25

0.84

0.58

0.65

0.64

−0.17

0.90

0.88

R Train

\({F}_{c}7\)

0.86

0.60

0.77

−0.12

0.61

0.56

0.70

0.73

0.69

\({F}_{c}28\)

0.92

−0.13

0.82

0.47

0.57

0.57

−0.12

0.90

0.90