Concerning the differentiability of the energy function in vector quantization algorithms

DOI10.1016/j.neunet.2006.11.006zbMath1123.68107DBLPjournals/nn/LepetzNA07OpenAlexW2038203824WikidataQ51917885 ScholiaQ51917885MaRDI QIDQ2643784

Max Némoz-Gaillard, Dominique Lepetz, Michaël Aupetit

Publication date: 27 August 2007

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2006.11.006

zbMATH Keywords

energy functionvector quantizationpotential functionself-organizing mapspseudo-potentialK-meansneural-gas

Mathematics Subject Classification ID

Nonnumerical algorithms (68W05) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An analysis of Kohonen's self-organizing maps using a system of energy functions
• Self-organized formation of topologically correct feature maps
• Self-organizing maps: Ordering, convergence properties and energy functions
• Self-organization and associative memory.
• Theoretical aspects of the SOM algorithm
• Convergence of the one-dimensional Kohonen algorithm
• Quantization
• A Stochastic Approximation Method

This page was built for publication: Concerning the differentiability of the energy function in vector quantization algorithms