Towards a unified hybrid model of category representation

The author (1991) has argued that existing symbolic and subsymbolic models of category representation fail to capture critical features of hierarchy and partonomy. In this paper a hybrid connectionist model that addresses these shortfalls is described. By way of demonstration, it is shown how it can deliver faster basic level categorization times in categorizing isolated objects, and equality of basic level and superordinate level categorization times of objects in scenes. The learning algorithm is described. This algorithm is unique in that it allows relearning of already-learned definitions under the guidance of a high-level symbol system