Neural network model of spatial memory

This paper offers a neural network model that can memorize and recall spatial maps. This is an improved version of the authors´ previous model (1996). When driving through a place we have been before, we can recall and imagine the scenery that we cannot see yet but shall see soon. Triggered by the newly recalled image, we can also recall other scenery further ahead of us. The proposed model emulates such a recalling process. In the computer simulation of the proposed model, we prepare a map of Europe and assume a situation where one (in this case, our model) makes a trip along railways. At first, the model wanders around Europe and captures and memorizes fragmentary maps around it. After that, the model makes another trip along a neighboring route. Whenever the model moves along a railway, the model recalls new maps ahead on the route from the memory. Thus, an image covering a wide area is retrieved by a continuous chain process of recalling. Even though the traveling route is novel to the model, the recalled maps are correct in most cases, if the model has made a trip in the neighborhood before. When the model visits a new place and fails to recall a correct map, the actual map around the model is simply added to its memory