Biot’s equations—inverse modeling: PINN performance as function of hyperparameters.
收藏数据链接：
官方服务：
资源简介：
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 is fixed at 250. Note that we pick the optimal hyperparameters, i.e., Nhl = 6 and Nn = 20 from the sensitivity analysis of the forward model. Results shown in this table are an average over 27 realizations.
创建时间：
2020-05-06
