Representation of our convolutional neural network architecture. We show a 2D histogram of an E as an input example. Different layers of the network are displayed in various colors. The network is composed of 2 blocks of convolution layers, convolution layer, max pooling, and dropout. Then, we flatten the input and use two fully connected layers followed by the output layer. The output consists of a neuron with softmax activation. Table A.2 show the hyperparameters used in this architecture.