Skip to main content
. 2022 Nov 3;7(45):41732–41743. doi: 10.1021/acsomega.2c05952

Table 2. GPR Training Result with Different Kernel Functionsa.

  RMSE R2 MSE MAE
GPR with the squared exponential kernel 16.287 0.97 265.27 5.8231
GPR with the rational quadratic kernel 7.9321 0.99 62.919 3.2494
GPR with the combined kernel 1.8060 1.00 3.262 1.2807
a

GPU is used for parallel computing.