The relationship between Kohonen learning and Kalman filters
Philip D. Picton · 1991
A considerable amount of research has been devoted to learning mechanisms where a set of input and output pairs are applied to a network, and the network adapts so that given the same set of inputs in the future it will produce the corresponding set of outputs. In practically all of these methods the starting point is Hebbian learning where weights on the inputs are strengthened if the output fires when any particular input fires. Kohonen learning, and the connection between learning in neural networks and adaption in Kalman filters are described.