The evaluate_tabular script was simplified to ease the analysis of more
quantities. Several coverage quantities and the bias were added to these
quantities. However, they perform rather poor.

This covers all regression datasets treated in the MC Dropout and Deep
Ensemble paper. Results are comparable or even better. For multivariate
dataset, the decouple_dimensions keyword in the evaluation scripts can
be used to follow the (rather weird) convention of these papers.

Both reaching similar RMSEs as in MC Dropout paper.
Updated hidden_layers handling in all training files.