About the multidimensional competitive learning vector quantization algorithm with constant gain

DOI10.1214/aoap/1034801249zbMath0892.60082MaRDI QIDQ1370999

Gilles Pagès, Catherine Bouton

Publication date: 9 August 1998

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aoap/1034801249

zbMATH Keywords

neural networks; Markov chain; vector quantization; uniform ergodicity

Mathematics Subject Classification ID

60J10: Markov chains (discrete-time Markov processes on discrete state spaces)

60J20: Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.)

60F99: Limit theorems in probability theory

Related Items

A space quantization method for numerical integration, Limit theorems for random normalized distortion, Simulated annealing with a potential function with discontinuous gradient on \(\mathbb R^d\), Error analysis of the optimal quantization algorithm for obstacle problems.

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Markov chains and stochastic stability
• Self-organization and a.s. convergence of the one-dimensional Kohonen algorithm with non-uniformly distributed stimuli
• Self-organization and associative memory
• Étude d'un processus d'auto-organisation. (Study of a self-organization process)
• Analysis of a simple self-organizing process
• A self-organizing cluster process
• On the a.s. convergence of the Kohonen algorithm with a general neighborhood function
• Exponential rate of convergence for Lloyd's method I
• Sufficient conditions for uniqueness of a locally optimal quantizer for a class of convex error weighting functions
• Convergence in Distribution of the One-Dimensional Kohonen Algorithms when the Stimuli are not Uniform