Feed-forward neural networks. In this exercise, we implement a feed-forward neural network for a binary classification task. The goal is to predict whether the e-mail is spam (labeled as 1) or not (0) according to its attributes (e.g., word frequency, length of uninterrupted sequence of capital letters). The detailed description of the data set can be found at http://archive.ics.uci. $edu/ml/$ datasets/Spambase. To complete this exercise, you are required to

a. construct a multilayer feed-forward neural network for the spam prediction task and evaluate the model from the following perspectives, including prediction accuracy, F₁ score, and AUC-ROC curve;

b. compare the performance of the models with various activation functions and different depth/width.