Title :
Stability analysis of self-organizing maps and vector quantization algorithms
Author :
Tucci, Mauro ; Raugi, Marco
Author_Institution :
Dept. of Electr. Syst. & Autom., Univ. of Pisa, Pisa, Italy
Abstract :
In this work a zero input stability analysis of the self-organizing map (SOM) learning algorithm and related unsupervised vector quantization algorithms is presented. The stability of the SOM incremental learning rule is analyzed using the theory of dynamical switched systems. The equation is demonstrated to be asymptotically stable under simple constraints on the learning parameters.
Keywords :
asymptotic stability; learning (artificial intelligence); self-organising feature maps; vector quantisation; asymptotically stable; dynamical switched systems; learning algorithm; self-organizing maps; stability analysis; unsupervised vector quantization algorithms; Algorithm design and analysis; Asymptotic stability; Convergence; Heuristic algorithms; Kernel; Stability analysis; Vector quantization;
Conference_Titel :
Neural Networks (IJCNN), The 2010 International Joint Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-6916-1
DOI :
10.1109/IJCNN.2010.5596939
