16 June 2024 09:14:50 PM

ppc_neural_pde_square():
  ppc_neural_pde() models a partial differential equation
  in the form of a boundary value problem, solved
  using a neural network.
  weights before training:
 -0.222 
  0.054 
 -0.023 
  0.129 
 -0.135 
  0.013 
  0.452 
  0.416 
  0.136 
  0.217 
 -0.358 
  0.107 
 -0.484 
 -0.257 
 -0.363 
  0.304 
 -0.343 
 -0.099 
 -0.370 
 -0.391 
Nelder-Mead: Converged after 3171 function evaluations
Nelder-Mead: Neural network’s residual error = 1.35314e-14
weights after training:
 14.292 
 -0.742 
 22.042 
  3.098 
  1.481 
 14.504 
 25.095 
 21.306 
-16.135 
-10.870 
-14.479 
  1.835 
 21.680 
  0.975 
 -2.750 
-34.495 
 -2.119 
  7.441 
-27.965 
  5.805 
Error versus the ODE’s exact solution = 0.919478

ppc_neural_ode_square():
  Normal end of execution.
16 June 2024 09:14:50 PM