Self-organized cognitive maps

This paper argues cognitive mapping is a learning process that can br simul ated by a sell-organizing neural network. The learning of city locations wa s considered in two studies. One study focused on the learning of city loca tions on four continents. Results indicated the neural network aligned the cities producing systematic errors similar to those in human cognitive maps . A second study had a neural network learn a biased sample of city locatio ns in the United States. Results indicated a non-linear relationship betwee n cognitive and physical distances. Self-organized cognitive maps naturally produce this non-linear relationship when information from more than one s cale is mapped into one space.