Obtaining Parton Distribution Functions from Self-organizing Maps *

We present an alternative algorithm to global fitting procedures to construct Par-ton Distribution Functions parametrizations. The proposed algorithm uses Self-Organizing Maps which at variance with the standard Neural Networks, are based on competitive-learning. Self-Organizing Maps generate a non-uniform projection from a high dimensional data space onto a low dimensional one (usually 1 or 2 dimensions) by clustering similar PDF representations together. The SOMs are trained on progressively narrower selections of data samples. The selection criterion is that of convergence towards a neighborhood of the experimental data. All available data sets on deep inelastic scattering in the kinematical region of 0.001 ≤ x ≤ 0.75, and 1 ≤ Q 2 ≤ 100 GeV 2 , with a cut on the final state invariant mass, W 2 ≥ 10 GeV 2 were implemented. The proposed fitting procedure, at variance with standard neural network approaches, allows for an increased control of the systematic bias by enabling the user to directly control the data selection procedure at various stages of the process.