Abstract
Self-organisation is displayed during the unsupervised learning of the Kohonen Neural Network (KNN) algorithm. Classical Markov techniques, the ordinary differential equation (ODE) method being included among these, have so far not yielded a complete general analysis of self-organisation in the KNN. In order to obtain a more general understanding of self-organising behaviour which could then be applied to the analysis of self-organisation in the KNN two simpler self-organising algorithms are described. The first algorithm is based on a simple intuitive understanding of self-organisation. The second is based on a simplification of the KNN algorithm. Using the ODE method general results on the self-organising abilities of the two algorithms are given.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
G. Nicolis and I. Prigogine. Exploring Complexity. W. H. Freeman, New York. 1989.
E. Jantsch. The Self-Organising Universe. Pergamon Press, Oxford, New York, 1980.
T. Kohonen. Speech Recognition based on topology preserving neural maps. Kogan Page, London. 1989.
F. Blayo and P. Desmartines. Kohonen algorithms: Application to the analysis of economic data. Bulletin des Schweizerischen Eletrotechnischen Vereins und des Verbandes Schweizerischer Elektrizitatswerke, 85(5):23–26, 1992. (in French).
E. Parzen. Stochastic Processes. Holden-Day, Inc., San Francisco, London, Amsterdam, 1962.
M. Cottrell and J.C. Fort. Étude d'un processus d'auto-organisation. Ann. Inst. Henri Poincaré, 23(1):1–20, Jan. 1987.
C. Bouton and G. Pagès. Self-organisation of the one-dimensional Kohonen algorithm with non-uniformly distributed stimuli. Stochastic Processes and their Applications, 47:249–274, 1993.
E. Erwin, K. Obermayer, and K. Schulten. Self-organising maps: Ordering, convergence properties and energy functions. Biol. Cybern., 67:47–55, 1992.
P. Thiran and M. Hasler. Self-organisation of a one dimensional Kohonen network with quantized weights and inputs. To appear in Neural Networks.
M. Cottrell, J.C. Fort, and G. Pagès. Two or three things we know about the Kohonen algorithm. In Proceedings of ESANN, 1994.
John A. Flanagan. Self-organising neural networks, 1994. Thèse no 1306 (1994) Electricity Department, EPFL, Lausanne, Switzerland.
L. Ljung. Analysis of recursive stochastic algorithms. IEEE Trans. on Automatic Control, AC-22(4):551–575, Aug. 1977.
H. J. Kushner and D. S. Clark. Stochastic Approximation Methods for Constrained and Unconstrained Systems, volume 26 of Applied Mathematical Sciences. Springer-Verlag, New York, Heidelberg, Berlin, 1978.
C. Bouton and G. Pagès. Convergence in distribution of the one-dimensional Kohonen algorithm when the stimuli are not uniform. Advances in Applied Probability, 26(1), March 1994.
M. Cottrell and J.C. Fort. A stochastic model of retinotopy: A self organising process. Biol. Cybern., 53:405–411, 1986.
W. Kaplan. Advanced Mathematics for Engineers. Addison-Wesley, New York, 1981.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Flanagan, J.A., Hasler, M. (1995). Self-organising Artifical Neural Networks. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_192
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_192
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive