Skip to main content

Table 12 Statistical error analysis of PINNs results for different values of time variable t to Example 4.3

From: A deep learning approach: physics-informed neural networks for solving a nonlinear telegraph equation with different boundary conditions

t

MAE

MSE

Range

Variance

Standard deviation

0.0

9.689e−07

9.205e−12

1.105e−06

2.106e−14

7.122e−07

0.1

8.643e−07

9.213e−12

1.119e−06

4.995e−13

7.122e−07

0.2

8.120e−07

9.34e−12

1.137e−06

5.072e−13

7.133e−07

0.3

9.689e−07

9.261e−12

1.408e−06

5.350e−13

7.067e−07

0.4

1.073e−06

9.309e−12

1.747e−06

5.848e−13

7.404e−07

0.5

1.483e−06

9.674e−12

1.788e−06

6.200e−13

7.723e−07

0.6

2.024e−06

9.870e−12

1.949e−06

6.964e−13

9.039e−07

0.7

3.105e−06

9.887e−12

2.002e−06

8.171e−13

9.658e−07

0.8

3.271e−06

9.991e−12

2.158e−06

9.329e−13

9.207e−07

0.9

3.490e−06

9.982e−12

2.593e−06

9.017e−13

9.496e−07

1.0

4.106e−06

9.997e−12

3.360e−06

9.774e−13

9.886e−07