An approach to the acquisition of a world frame using a visual associative memory

An approach to the autonomous acquisition of world knowledge is presented. Based on the theory that biological cognizance is essentially a Gestalt awareness of the world, our research attempts to develop a similar awareness using an associative memory. This associative memory receives inputs from several self-organizing feature maps which identify objects in particular parts of an image. Spatial relationships of objects in the image are reflected in the relationship of the feature maps to each other, so the associative memory records both identity and spatial information of objects. To this visual memory is added the memory of the viewer's internal status, in this case an estimate of position. Together, these associative memories provide a view-field model of location awareness similar to that originally presented by D. Zipser (1986). In keeping with the Gestalt approach taken here, the grandmother cell approach of the earlier work has been replaced by the use of distributed representations. View-fields are identified as a pattern of activity across a number of nodes. It is believed that this distributed approach will permit greater generalization on the part of the viewer and provide a larger memory capacity than can be achieved otherwise. >