Exploring Physics-Informed Neural Networks for the Generalized Nonlinear Sine-Gordon Equation

Figure 3

Train and test loss of PINN process for 15000 epochs (training iterations) for the dirichlet BCs case by using (a) adam, (b) L-BFGS-B, and (c) combined adam and L-BFGS-B optimization algorithms.

(a)

(b)

(c)