The goal of this contest is to implement the regularization methods discussed in class in order to build an ANN model of a prescribed architecture that generalizes best on test data. The measuring metric is accuracy score. The winning model will be the one with the highest accuracy score on the hidden test set. NOTE: Highest accuracy on public leaderboard does not imply best model because the final winner is announced based on a hidden test set. This set will be made public only at the end of the competition.