TY - GEN

T1 - Self-organizing feature map with a momentum term

AU - Hagiwara, Masafumi

N1 - Copyright:
Copyright 2009 Elsevier B.V., All rights reserved.

PY - 1993

Y1 - 1993

N2 - 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 = Σμn αn-μ Eμ, where Eμ 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.

AB - 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 = Σμn αn-μ Eμ, where Eμ 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.

UR - http://www.scopus.com/inward/record.url?scp=0027848472&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027848472&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027848472

SN - 0780314212

SN - 9780780314214

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 467

EP - 470

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

T2 - Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)

Y2 - 25 October 1993 through 29 October 1993

ER -