Abstract
The self-organizing feature map (SOFM) algorithm can be generalized, if the regular neuron grid is replaced by an undirected graph. The training rule is furthermore very simple: after a competition step, the weights of the winner neuron and its neighborhood must be updated. The update is based on the generalized adjacency of the initial graph. This feature is invariant during the training; therefore its derivation can be achieved in the preprocessing. The newly developed self-organizing neuron graph (SONG) algorithm is applied in function approximation, character fitting and satellite image analysis. The results have proven the efficiency of the algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G.A. Carpenter: Neural network models for pattern recognition and associative memory, Neural Network, 1989, 2, 243–257
M. Minsky, S. Papert: Perceptrons: An introduction to computational geometry, MIT Press, Cambridge, 1969 and 1972
Ch. von der Malsburg: Self-organization of orientation sensitive cells in the striate cortex, Kybernetik, 1973, 14, 85–100
S. Grossberg: Adaptive pattern recognition and universal recoding, Parallel development and coding of neural feature detectors, Biological Cybernetics, 1976, 23, 121–134
G.A. Carpenter, S. Grossberg: A massively parallel architecture for self-organizing neural pattern recognition machine, Computer Vision, Graphics and Image Processing, 1987, 37, 54–115
T. Kohonen: Self-Organization and associative memory, Springer, Berlin, 1984
T. Kohonen: Self-Organizing Maps, Springer, Berlin, 1995
G.A. Carpenter, S. Grossberg (Eds): Pattern recognition by self-organizing neural network, MIT Press, Cambridge, 1991
D.M. Kammen: Self-organization in neural networks, Harvard University, Cambridge, 1988
H. Demuth — M. Beale: Neural Network Toolbox, For Use with MATLAB, User’s Guide, The MathWorks, Natick, 1998
B. Bollobás: Modern Graph Theory, Springer Verlag, New York, 1998
R. Balakrishnan: A Textbook of Graph Theory, Springer Verlag, New York, 2000
F. Buckley, F. Harary: Distance in Graphs, Addison-Wesley, Redwood City, 1990
T. Ottmann, P. Widmayer: Algorithmen und Datenstrukturen, Wissenschaftsverlag, Mannheim, 1993
W.K. Chen: Applied Graph Theory, Graphs and Electrical Networks, North-Holland, Amsterdam, 1976
R.G. Busacker, T.L. Saaty: Endliche Graphen und Netzwerke, Eine Einführung mit Anwendungen, Oldenbourg, München, 1968
E.J. Henley, R.A. Williams: Graph Theory in Modern Engineering, Academic Press, New York, 1973
I.N. Bronstein, K.A. Semendjajev, G. Musiol, H. Mühlig: Taschenbuch der Mathematik, Verlag Harri Deutsch, Frankfurt am Main, 2000, pp. 359–371
M.N.S. Swamy, K. Thulasiraman: Graphs, Networks and Algorithms, Wiley, New York, 1981
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Barsi, A. (2003). Neural Self-Organization Using Graphs. In: Perner, P., Rosenfeld, A. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2003. Lecture Notes in Computer Science, vol 2734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45065-3_30
Download citation
DOI: https://doi.org/10.1007/3-540-45065-3_30
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40504-7
Online ISBN: 978-3-540-45065-8
eBook Packages: Springer Book Archive