References in periodicals archive ?
ANFIS, FFNN, FITNET, CFNN, GRNN, CART, SVR and MLR models were trained and tested with the dataset of atomic coordinates for CNTs.
FFNN, FITNET and CFNN models have 3 layers (input, hidden and output) and the input and output layers have 5 and 3 neurons respectively.
Table 3, Table 4 and Table 5 summarize the performance results of u', v' and w' coordinates prediction using ANFIS, FFNN, FITNET, CFNN, GRNN, SVR, CART and MLR models respectively.
However, the results of ANFIS, FFNN, FITNET and CFNN models have a superiority over other models.
FEM 45.00 1.26 15000 ANFIS 0.003 0.001 280 NARXNN 0.161 0.002 1364 NARNN 0.033 0.002 19 LRNN 2.372 0.374 266 CFNN 0.169 0.032 283 FFNN 0.159 0.003 45000 POLY 0.001 0.001 15000
Acronyms browser ?
Full browser ?