Fig. 2: DNN Performance under different batch numbers and training ratios. | npj Computational Materials

Fig. 2: DNN Performance under different batch numbers and training ratios.

From: Accelerated design and characterization of non-uniform cellular materials via a machine-learning based framework

Fig. 2

a Effect of batch number on convergence. b Effect of batch number on the performance in terms of probability P(−0.1 < NE < 0.1) and MSE. c Effect of training ratio on convergence. d Effect of batch number on the performance in terms of probability P(−0.1 < NE < 0.1) and MSE.

Back to article page