Convergence in distributions of the multi-dimensional Kohonen algorithm
Discrete-time Markov processes on general state spaces (60J05) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Neural networks for/in biological studies, artificial life and related topics (92B20)
\textit{T. Kohonen} [Biol. Cybern. 43, 59-69 (1982; Zbl 0466.92002)] introduced the self-organizing map (SOM) as a simple model of a process of self-organization between different areas of the cortex and different sensory inputs. See also \textit{T. Kohonen} [``Self-organizing maps (1994; Zbl 0827.68092)] and the author [``A mathematical study of self-organizing neural networks (Shaker, Aachen)]. The simplicity of its learning algorithm immediately made the map interesting for many artificial intelligence applications, e.g., clustering, feature mapping and building topology preserving maps. Besides the feedforward neural networks, which are designed for supervised learning, SOM is the most well known neural network with a reasonable capability for unsupervised data analysis.NEWLINENEWLINENEWLINEIn the present paper, the author considers the Kohonen algorithm with a constant learning rate as a Markov process evolving in a topological space. Despite the fact that this algorithm is neither weak nor strong Feller, he shows that it is a \(T\)-chain, regardless of the dimensionalities of both data space and the special shape of the neighborhood function. Furthermore, in the case of a multidimensional setting, which is practically important, the author shows that the chain is \(\Psi\)-irreducible and aperiodic. He then shows that Doeblin's condition is valid, which ensures the convergence in distribution of the process to an invariant probability measure with a geometric rate. Finally, he shows that the process is Harris recurrent, which enables the use of statistical devices to measure the centrality and variability of the invariant probability measure.
- Convergence in Distribution of the One-Dimensional Kohonen Algorithms when the Stimuli are not Uniform
- scientific article; zbMATH DE number 447040
- Convergence of the one-dimensional Kohonen algorithm
- On the a.s. convergence of the Kohonen algorithm with a general neighborhood function
- Self-organization and a.s. convergence of the one-dimensional Kohonen algorithm with non-uniformly distributed stimuli
- Étude d'un processus d'auto-organisation. (Study of a self-organization process)
- Kohonen neural networks and genetic classification
- SOM's mathematics
- scientific article; zbMATH DE number 447040 (Why is no real title available?)
- The convergence of an MED iterative algorithm for the kurtosis norm
- Convergence in Distribution of the One-Dimensional Kohonen Algorithms when the Stimuli are not Uniform
- scientific article; zbMATH DE number 2044687 (Why is no real title available?)
- One-dimensional Kohonen maps are super-stable with exponential rate
- Self-organizing maps, theory and applications
This page was built for publication: Convergence in distributions of the multi-dimensional Kohonen algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2731157)
