A conditional, a fuzzy and a probabilistic interpretation of self-organizing maps

In this paper we establish a link between fuzzy and preferential semantics for description logics Self-Organising Maps, which have been proposed as possible candidates to explain the psychological mechanisms underlying category generalisation. particular, show that input/output behavior of Map after training can be described by logic interpretation well interpretation, based on concept-wise multipreference semantics, takes into account preferences with respect different concepts has recently ranked weighted defeasible logics. Properties network proven model checking or interpretation. Starting from also provide probabilistic neural model.