Title :
Self-organization in cellular neural networks: a comparison with Kohonen´s self-organizing maps
Author_Institution :
Fed. Inst. of Technol., Lausanne, Switzerland
Abstract :
The ordinary differential equation (ODE) method is difficult to use for analyzing the self-organization of the Kohonen algorithm. Two stochastic, `self-organizing´ algorithms, whose corresponding ODE is a CNN equation, are presented. Their convergence shares similar features with the Kohonen self-organizing process
Keywords :
asymptotic stability; cellular neural nets; convergence; differential equations; probability; self-organising feature maps; stochastic processes; unsupervised learning; Kohonen self-organizing maps; asymptotic stability; cellular neural networks; convergence; differential equation; probability; stochastic process; unsupervised learning; Algorithm design and analysis; Cellular neural networks; Convergence; Differential equations; Intelligent networks; Network topology; Neurons; Self organizing feature maps; Stochastic processes; Unsupervised learning;
Conference_Titel :
Cellular Neural Networks and Their Applications Proceedings, 1998 Fifth IEEE International Workshop on
Conference_Location :
London
Print_ISBN :
0-7803-4867-2
DOI :
10.1109/CNNA.1998.685332
