The development of an associative memory model based on a classifier

Summary form only given, as follows. A model for an associative memory based on a classifier is presented. It is assumed that any object retrieved by the memory can be classified into one of a number of general object classes. In a training phase, a set of classified examples typical of the object classes is presented to the model. The model automatically develops internal representations of the object classes. During the normal processing phase input consists of an incomplete description of an object and a classification requirement. The target function of the model is to return the complete description of an object, which matches the partial description and satisfies the classification requirement. The model is developed by introducing feedback in a neural network for pattern classification. This functionality is different from that of existing associative memory models, and it is of use in problems where the class of the retrieved object is of importance.<>