Kohonen neural networks and genetic classification

DOI10.1016/J.MCM.2006.04.004MaRDI QIDQ2471604zbMATH OpenOpenAlexWikidataFDO

Authors Daniela Bianchi, Raffaele Calogero, Brunello Tirozzi

Publication date 22 February 2008

Published in Mathematical and Computer Modelling (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0809.4755

zbMATH Keywords

almost everywhere convergencegeneticsKohonen neural networklearning parametermicroarraysneighborhood functionup modulated genes

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: We discuss the property of a.e. and in mean convergence of the Kohonen algorithm considered as a stochastic process. The various conditions ensuring the a.e. convergence are described and the connection with the rate decay of the learning parameter is analyzed. The rate of convergence is discussed for different choices of learning parameters. We proof rigorously that the rate of decay of the learning parameter which is most used in the applications is a sufficient condition for a.e. convergence and we check it numerically. The aim of the paper is also to clarify the state of the art on the convergence property of the algorithm in view of the growing number of applications of the Kohonen neural networks. We apply our theorem and considerations to the case of genetic classification which is a rapidly developing field.

Recommendations

• Convergence of the one-dimensional Kohonen algorithm
• Self-organization and a.s. convergence of the one-dimensional Kohonen algorithm with non-uniformly distributed stimuli
• scientific article; zbMATH DE number 447040
• Convergence in distributions of the multi-dimensional Kohonen algorithm
• Convergence in Distribution of the One-Dimensional Kohonen Algorithms when the Stimuli are not Uniform

Cites work

• An analysis of Kohonen's self-organizing maps using a system of energy functions
• Analysis of a simple self-organizing process
• Convergence in distributions of the multi-dimensional Kohonen algorithm
• Convergence theorems for the Kohonen feature mapping algorithms with VLRPs
• scientific article; zbMATH DE number 3469876 (Why is no real title available?)
• scientific article; zbMATH DE number 3553601 (Why is no real title available?)
• scientific article; zbMATH DE number 1273988 (Why is no real title available?)
• On the a.s. convergence of the Kohonen algorithm with a general neighborhood function
• On the rate of convergence in topology preserving neural networks
• On the stationary state of Kohonen's self-organizing sensory mapping
• Rigorous solution of the Gardner problem
• Self-organization and a.s. convergence of the one-dimensional Kohonen algorithm with non-uniformly distributed stimuli
• Self-organizing maps: Ordering, convergence properties and energy functions
• Self-organizing maps: Stationary states, metastability and convergence rate
• Significance analysis of microarrays applied to the ionizing radiation response
• The free energy of a class of Hopfield models
• Étude d'un processus d'auto-organisation. (Study of a self-organization process)

Cited in

(4)

• Neural network classification of word evoked neuromagnetic brain activity
• scientific article; zbMATH DE number 2042268 (Why is no real title available?)
• scientific article; zbMATH DE number 1784871 (Why is no real title available?)
• Convergence theorems for the Kohonen feature mapping algorithms with VLRPs

This page was built for publication: Kohonen neural networks and genetic classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2471604)