A stochastic trained neural network for nonparametric hypothesis testing

The present work is oriented to the description and evaluation as a nonparametric hypothesis test of Genetic Inside Neural Network (GINN) based on an artificial neural network trained with a stochastic process. In this paper, the theoretical framework is detailed, together with the convergence properties, and the way it is implemented. Finally, some studies with simulated and real data show the stability of results and prediction capacity.