Map learning using associative memory neural network

Summary form only given. Map learning using associative memory is considered. Given a source location and a destination location to be visited and its associated visiting path, an associative memory neural network which can remember and recall all possible paired-location combinations is constructed. Kth nearest neighbor transformation (Knn) is used to transfer the input paired locations to a vector form indicating the neighboring information among all the locations in the map. Training patterns are selected from the linear combination of the eigenvector of the covariance matrix of the associative group and the input vectors. By training the network with the selected transformed training vectors, the best path of any two points in the map can be obtained. An example of learning the city map of Dayton, Ohio, is used to illustrate the proposed network