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 a self-organizing feature map algorithm having the momentum term through the following assumptions: 1) The cost function is Eⁿ = Σ_μⁿ α^n-μ E_μ, where E_μ is the modified Lyapunov function originally proposed by Ritter and Schulten at the μ th learning time and α is the momentum coefficient. 2) The latest weights are assumed in calculating the cost function Eⁿ. 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.