Table 7 Performance boost of PINN on the Helmholtz benchmarks using transfer learning
From: Transfer learning for deep neural network-based partial differential equations solving
Subtask | Original | Transfer | Boost |
|---|---|---|---|
case 2 | 1.04e+00 | 6.03e-01 | 42.0% |
case 3 | 1.37e-01 | 9.91e-02 | 27.7% |
case 4 | 5.48e-01 | 1.70e-01 | 69.0% |
case 5 | 3.14e+00 | 1.13e+00 | 64.0% |
case 6 | 4.95e+00 | 3.22e+00 | 34.9% |
case 7 | 6.08e+00 | 2.68e+00 | 55.9% |
case 8 | 7.21e+00 | 2.83e+00 | 60.7% |