FIG. 6.

No feature selection: $u_t=f^u(u,u_x,u_{xx},v,v_x,v_{xx})$ and $v_t=f^v(u,u_x,u_{xx},v,v_x,v_{xx})$. Regression results of the two methods for time derivatives: Gaussian processes (GPs) and neural networks (NNs).