Seismic Failure Probability of a Curved Bridge Based on Analytical and Neural Network Approaches

Table 2

The network training parameters.

Parameter	Value
The network parameters in each group
Number of training examples (randomly)	90
Number of training examples (randomly)	19
Number of testing examples (randomly)	20
Iteration number (maximum)	1000
Learning rate (lr)	1
Momentum constants	0.5
Error tolerance	0.001
ANN structure	8:HN:4