Using ANNs on small data – Deep Learning vs. Xgboost

Andrew Beam does a great job showing that small datasets are not off limits for current neural net methods. If you use the regularisation methods at hand – ANNs is entirely possible to use instead of classic methods. Let's see how this holds up on up on some benchmark datasets. Let's start with the iris dataset that you nicely can pull with the pandas read_csv function right of the internets. We create a feature matrix X and a target y from the Pandas dataframe.