Shape recognition with nearest neighbor isomorphic network

Summary form only given. The nearest-neighbor isomorphic network (NNIN) paradigm is a combination of sigma-pi units in the hidden layer and product units in the output layer. Good initial weights can be found through clustering of the input training vectors, and the network can be successfully trained via back-propagation (BP) learning. Theoretical conditions under which the product operation can replace the Min operation were found. Under some sufficient conditions, the product operation yields the same classification result as the Min operation. The algorithm was applied to a geometric shape recognition problem, and the performances were compared with those of two other well-known algorithms