NETCLASS-a fresh look at connectionist category formation

The author describes the connectionist categorisation model NETCLASS, a proposed neural solution to the problem of category formation and representation. Superordinates in NETCLASS have a fundamentally disjunctive representation. They are also strongly related to the actual scenes in which they are grouped. It is shown how these features, along with NETCLASS´ connectionist nature, give a better account of some of the more recent data on superordinate categories than that offered by existing categorization models. Disjunction turns out to be of use in representing components. It is suggested that this offers a solution to a problem inherent in neural net concept component representation