Gap Prediction in Hybrid Graphene-Hexagonal Boron Nitride Nanoflakes Using Artificial Neural Networks

Figure 4

Histograms of coefficients for (a) Method 1 and (b) Method 2 corresponding to a different number of neurons in the hidden layer . An ensemble of 2000 starting configurations of ANNs were considered to construct the distributions.

(a) Method 1

(b) Method 2