Self-organizing feature map with a momentum term

Abstract

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 a self-organizing feature map algorithm having the momentum term through the following assumptions: 1) The cost function is E/sup n/=/spl Sigma//sub /spl mu///sup n//spl alpha//sup n-/spl mu//E/sub /spl mu//, where E/sub /spl mu// is the modified Lyapunov function originally proposed by Ritter and Schulten (1988, 1992) at the /spl mu/th learning time and /spl alpha/ is the momentum coefficient. 2) The latest weights are assumed in calculating the cost function E/sup 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.