On the rate of convergence in topology preserving neural networks

DOI10.1007/BF00197290MaRDI QIDQ808996zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Z.-P. Lo, B. Bavarian

Publication date 1991

Published in Biological Cybernetics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/bf00197290

zbMATH Keywords

error measure functionalfeature mapsKohonen learningmexican hutneighborhood interaction functionrate of self- organization to final equilibrium statetopology preserving unsupervised neural network

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Review text

Kohonen learning (and his feature maps) attracts still more attention of neural network people. Perhaps everybody who worked with it faced the question of proper choice of time-dependent gain and shrinking coefficients as well as the good choice of the ``mexican hut. The paper uses Gaussian type of the latter and shows that this ``neighborhood interaction function leads to a faster convergence.

Recommendations

• scientific article; zbMATH DE number 1555927
• On the convergence of a growing topology neural algorithm
• On convergence rate of projection neural networks
• Topology of deep neural networks
• scientific article; zbMATH DE number 1784858
• Rate of convergence of some neural network operators to the unit-univariate case
• Rate of convergence of some neural network operators to the unit-univariate case, revisited
• scientific article; zbMATH DE number 1182753
• Interpolation and rates of convergence for a class of neural networks
• Rate of convergence of some multivariate neural network operators to the unit

Cites work

• A stochastic model of retinotopy: A self organizing process
• Analysis of a simple self-organizing process
• Convergence properties of Kohonen's topology conserving maps: Fluctuations, stability, and dimension selection
• Formation of topographic maps and columnar microstructures in nerve fields
• On the stationary state of Kohonen's self-organizing sensory mapping
• Self-organization and associative memory.
• Self-organized formation of topologically correct feature maps

Cited in

(18)

• The effect of sample size on the extended self-organizing map network -- a market segmentation application
• Convergence properties of Kohonen's topology conserving maps: Fluctuations, stability, and dimension selection
• Self-organizing maps: Stationary states, metastability and convergence rate
• Self-organizing maps: Ordering, convergence properties and energy functions
• A self-organizing cluster process
• Clustering: a neural network approach
• Study of the Kohonen network with a discrete state space
• Conformality in the self-organization network
• Alternative learning vector quantization
• Kohonen neural networks and genetic classification
• On the convergence of a growing topology neural algorithm
• Self-organization of the batch Kohonen network under quantization effects
• scientific article; zbMATH DE number 1555927 (Why is no real title available?)
• scientific article; zbMATH DE number 1784871 (Why is no real title available?)
• The Time-Organized Map Algorithm: Extending the Self-Organizing Map to Spatiotemporal Signals
• Extending the Kohonen self-organizing map networks for clustering analysis.
• Convergence theorems for the Kohonen feature mapping algorithms with VLRPs
• Self-organizing map for symbolic data

This page was built for publication: On the rate of convergence in topology preserving neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q808996)