Abstract

This work presents an original algorithmic model of some essential features of psychogenetic theory, as was proposed by J.Piaget. Specifically, we modeled some elements of cognitive structure learning in children from 0 to 4 months of life. We are in fact convinced that the study of well-established cognitive models of human learning can suggest new, interesting approaches to problem so far not satisfactorily solved in the field of machine learning. Further, we discussed the possible parallels between our model and subsymbolic machine learning and neuroscience. The model was implemented and tested in some simple experimental settings, with reference to the task of learning sensorimotor sequences.