Self-organizing feature map with a momentum term

The objectives of this paper are to derive a momentum term in the Kohonen's self-organizing feature map algorithm theoretically and to show the effectiveness of the term by computer simulations. We will derive the self-organizing feature map algorithm having the momentum term through the following assumptions: (1) The cost function is E(n) = Sigma(mu)(n) alpha(n-mu)E(mu), where E(mu) is the modified Lyapunov function originally proposed by Ritter and Schulten at the mu th learning time and alpha is the momentum coefficient. (2) The latest weights are assumed in calculating the cost function E(n). According to our simulations, it has shown that the momentum term in the self-organizing feature map can considerably contribute to the acceleration of the convergence.