-
Biot’s equations—forward modeling: PINN performance as function of training s...
Sum of relative errors between the exact and predicted values of u, v, and p for the validation set. The table shows the dependency on the number of the initial and boundary... -
Excess Enthalpy, Density, and Speed of Sound for the Ternary Mixture Methyl <...
Excess molar enthalpies, HE(x, T), at T = 298.15 K, densities, ρ(x, T), and speeds of sound, u(x, T), at temperatures T = (288.15 to 308.15) K and atmospheric pressure have been... -
Linear Free-Energy Relationships and the Density Functional Theory: An Analo...
Density functional theory has been applied to describe electronic substituent effects, especially in the pursuit of linear relationships similar to those observed from physical... -
r37980778c78--93f73fdeafca4effdd1457db3b6f905e
Originally published in Optics Express on 03 November 2014 (oe-22-22-27739) -
Biot’s equations—forward modeling: PINN performance as function of hyperparam...
Sum of relative errors between the exact and predicted values of u, v, and p for the validation set. The table shows the dependency on the different number of hidden layers,... -
Media 1: Light-opals interaction modeling by direct numerical solution of Max...
Originally published in Optics Express on 03 November 2014 (oe-22-22-27739) -
r37980778c78--a8fb412b76a2be3a44616a7bbe79d62a
This figure shows the average percentage errors of θ1, θ2, θ3, θ4, and θ5 for different numbers of training data Ntr corrupted by different noise levels (ϵ). Here, the neural... -
Media 2: Light-opals interaction modeling by direct numerical solution of Max...
Originally published in Optics Express on 03 November 2014 (oe-22-22-27739) -
Diffusivity equation—forward modeling: PINN performance as function of traini...
Relative errors between the exact and predicted values of p for the validation set. The table shows the dependency on the number of the initial and boundary training data, Nb,... -
r37980778c78--d9507f0882c63969978cec0c219aa505
Relative error of p and percentage error of θ1 and θ2 for different number of hidden layers, Nhl, and different number of neurons per layer, Nn. The Ntr is fixed at 250. Note... -
Biot’s equations—inverse modeling: PINN performance as function of hyperparam...
Relative error of p, u, and v and percentage error of θ1, θ2, θ3, θ4, and θ5 for different number of hidden layers, Nhl, and different number of neurons per layer, Nn. The Ntr... -
Parameters used in the model.
Abbreviations: s.e. standard error; CR-BSI catheter related bloodstream infection; ICU intensive care unit; Q–E quasi-experimental; AUD Australian dollar; ec. eval'n economic... -
Diffusivity equation—inverse modeling: PINN performance as function of noise.
This figure shows the average percentage errors of θ1 and θ2 for different numbers of training data, Ntr, as function of the noise levels. Here, the neural network architecture...
