Abstract
The ASSOM is a self-organising neural network with the capability of adapting to linear subspaces. Here we propose two new methods to train the ASSOM network. A nonlinear system of equations is derived for network training. This system can be solved by a gradient-based approach or by the Levenberg–Marquardt method. Each of these two approaches gives a different learning rule. A comparison is carried out among the original Kohonen’s method and the proposed learning rules. Experimental results are reported, including a convergence speed experiment and a speech processing application, which show that the new learning rules have better performance than the original one.
Similar content being viewed by others
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
López-Rubio, E., Muñoz-Pérez, J., Gómez-Ruiz, J. et al. New learning rules for the ASSOM network. Neural Comput&Applic 12, 109–118 (2003). https://doi.org/10.1007/s00521-003-0376-x
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s00521-003-0376-x