It is widely accepted that correctly accounting for polarization within simulations involving water is critical if the structural, dynamic and thermodynamic properties of such systems are to be accurately reproduced. We propose a novel potential for the water dimer, trimer, tetramer, pentamer, hexamer that includes polarization explicitly, for use in Molecular Dynamics simulations. Using thousands of dimer, trimer, tetramer, pentamer and hexamer clusters sampled from a Molecular Dynamics simulation lacking polarization, we train (Artificial) Neural Networks (NNs) (also known as multilayer perceptrons), and other machine learning methods, to predict the atomic multipole moments of a central water molecule.