Abstract
This paper presents a new model of an artificial neural network solving classification problems — Local Transfer Function Classifier (LTF-C). Its structure is very similar to this of the Radial Basis Function neural network (RBF), however it utilizes entirely different learning algorithms, including not only changing positions and sizes of neuron reception fields, but also inserting and removing neurons during the training. Applying this network to practical tasks, such as handwritten digit recognition, shows, that it is characterized by high accuracy, small size and high speed of functioning.
This is a preview of subscription content, log in via an institution to check access.
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
Fiesler, E., Beale, R. (ed.): Handbook of neural computation. Oxford University Press, Oxford (1997)
Hebb, D.O.: The Organization of Behaviour. Wiley, New York (1949)
Pham, D.T., Xing, L.: Neural Networks for Identification, Prediction and Control. Springer Verlag, London (1995)
Le Cun, Y.: The MNIST database of handwritten digits. http://www.research. att.com/~yann/exdb/mnist/index.html
Le Cun, Y., et al.: Comparison of learning algorithms for handwritten digit recognition. In: Fogelman, F., Gallinari, P. (eds.): International Conference on Artificial Neural Networks. Paris (1995) 53–60
Mertz, C.J., Murphy, P.M.: UCI repository. http://www.ics.uci.edu/pub/ machine-learning-databases
Michie, D., Spiegelhalter, D.J., Taylor, C.C.: Machine Learning, Neural and Statistical Classification. Elis Horwood, London (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wojnarski, M. (2002). LTF-C — Neural Network for Solving Classification Problems. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Waśniewski, J. (eds) Parallel Processing and Applied Mathematics. PPAM 2001. Lecture Notes in Computer Science, vol 2328. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48086-2_71
Download citation
DOI: https://doi.org/10.1007/3-540-48086-2_71
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43792-5
Online ISBN: 978-3-540-48086-0
eBook Packages: Springer Book Archive