Abstract
In the context of supervised vectorial quantization (VQ) learning algorithms, we present an algorithm (SLTI) that exploits the self-organizing properties arising from a particular process of temporal inhibition of the winning units in competitive learning. This exploitation consists of establishing independence capabilities in the initialization of the prototypes (weight vectors), together with generalization capabilities, which to a certain extent solve some of the critical problems involved in the use of conventional algorithms such as LVQs and DSM. Another original aspect of this paper is the inclusion in SLTI of a simple rule for prototype adaptation, which incorporates certain useful features that make possible to plan the configuration of the SLTI parameters with specific goals in order to approach classification tasks of varied complexity and natures (versatility). This versatility is experimentally demonstrated with synthetic data comprising non linearly-separable classes, overlapping classes and interlaced classes with a certain degree of overlap.
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
[Ferri92] F. Ferri, E. Vidal, “Small Sample Size Effects in the Use of Editing Techniques”, International Conference on Pattern Recognition (ICPR 92). The Hague. pp. 607–610, 1992.
[Geva91] Geva, S.; Sitte, J. “Adaptive Nearest Neighbor Pattern Classification”, IEEE Trans. on Neural Networks, Vol. 2, No. 2, pp. 318–322, 1991.
[Hart68] P.E. Hart, “The Condensed Nearest Neighbor Rule.”, IEEE Trans. Information Theory, Vol. 125, 1968.
[Koh88] T. Kohonen; C. Barna and R. Chrisley, “Statistical Pattern Recognition with Neural Networks: Benchmarking Studies”, Procs. IEEE Int. Conf. on Neural Networks, ICNN-88, San Diego, Cal.; pp. I-61–I-68, 1988.
[Koh90] T. Kohonen, “The self-organizing map”, Proc. of the IEEE, Vol. 78, No. 9; pp. 1464–1480; 1990.
[Koh95] T. Kohonen: “Self-Organization Maps”; Springer-Verlag; 1995.
[Lang88] K.J. Lang, M.J. Witbrock, “Learning to Tell Two Spirals Apart”, Proc. of the 1988 Conectionist Models Summer School, Morgan Kaufmann, 1988.
[Mar97] Martín-Smith, P.: “Un nuevo modelo de red neuronal con aprendizaje competitivo”. PhD Thesis, University of Granada. November, 1997.
[Mar98] Martin-Smith, P. et al: “Self-Organization by Temporal Inhibition”. Sent to Neural Processing Letters, Kluwer Ac. Publish.
[Per93] J.C. Pérez, E. Vidal, “Constructive design of LVQ and DSM Classifiers”, Lecture Notes in Computer Science 686, Springer Verlag, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Martín-Smith, P., Pelayo, F.J., Ros, E., Prieto, A. (1999). Supervised VQ learning based on temporal inhibition. In: Mira, J., Sánchez-Andrés, J.V. (eds) Foundations and Tools for Neural Modeling. IWANN 1999. Lecture Notes in Computer Science, vol 1606. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0098219
Download citation
DOI: https://doi.org/10.1007/BFb0098219
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66069-9
Online ISBN: 978-3-540-48771-5
eBook Packages: Springer Book Archive