Abstract
This paper analyzed several commonly used supervised and unsupervised training algorithms and discusses how they can be unified into a unique training algorithms.
The rationale of this work is to use a traditional gradient descent algorithm, for supervised training, while, for unsupervised training, to self-compute a target vector, in an unsupervised fashion, to be applied then to a supervised algorithm.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
S. Haykin, “Neural Networks: A Comprehensive Foundation”, Mc Millan College Publishing Company, New York, 1994.
Q. Zhang, “Using Wavelet Networks in Non-parametric Estimation”, IEEE Trans. on Neural Networks, Vol. 8, No. 2, March 1997, pp. 227–236.
L. Wang, “Adaptive Fuzzy Systems and Control”, Prentice Hall, Englewood Cliffs, New Jersey, 1994.
T.J. Ross, “Fuzzy Logic with Engineering Applications”, chapte 11, McGraw Hill, New York, 1995.
J.S. Roger Jang, C.T. Sun, “Functional Equivalence Between Radial Basis Function Networks and Fuzzy Inference Systems”, IEEE Trans. Neural Networks, Vol. 4, no. 1, January 1993, pp. 156–159.
L.M. Reyneri, “Unification of Neural and Fuzzy Computing Paradigms”, Proc. of 1-st Int’s Symposium on Neuro-Fuzzy Systems, AT 96, Lausanne (CH), August 1996, sect. 2-Tutorials.
L.M. Reyneri, “Unification of Neural and Wavelet Networks and Fuzzy Systems”, to be published in IEEE Trans. on Neural Networks, 1999.
K.J. Hunt, R. Haas, R. Murray Smith, “Extending the Functional Equivalence of Radial Basic Function Networks and Fuzzy Inference Systems”, IEEE Trans. Neural Networks, Vol. 7, no. 3, may 1996, pp. 776–781.
T. Takagi, M. Sugeno, “A New Approach to the Design of Fuzzy Controllers”, Advance in Fuzzy Sets, Possibility Theory, and Applications, P. Wang and S. Chang eds.), Plenum, New York, 1983, pp. 325–334.
J.M. Benitez, J.L. Castro, I. Requena, “Are Artificial Neural Networks Black Boxes”, IEEE Trans. Neural Networks, Vol. 8, no. 5, September 1997, pp. 1156–1164.
V. Colla, L.M. Reyneri, M. Sgarbi, “Parametric Characterization of Jominy Profiles in Steel Industry by Means of Wavelet and Neural Networks”, to be printed in Journal Integrated Computer Aided Engineering, John Wiley & Sons, New York.
T. Sudkamp, R.J. Hammell, II, “Interpolation Completion and Learning Fuzzy Rules”, IEEE Trans. Systems, Man and Cybernetics, Vol. 24, 1994, pp. 103–106.
S. Chen, C.F.N. Cowan, P.M. Grant, “Orthogonal least Squares Learning Algorithm for Radial Basis Function Networks”, IEEE Trans. Neural Networks, Vol. 2, March 1991, pp. 302–309.
L.M. Reyneri, E. Filippi, “An Analysis on the Performance of Silicon Implementations of Backpropagation Algorithms for Artificial Neural Networks”, IEEE Transactions on Computers, special issue on Artificial Neural Networks, Vol. 40, no. 12, December 1991, pp. 1380–1389.
L.M. Reyneri, M. Sgarbi, “Performance of Weighted Radial Function Classifiers”, in Proc. of ESANN 97, Bruges (B), April 1997, pp. 19–25.
V. Colla, M. Sgarbi, L.M. Reyneri “A Comparison Between Weighted Radial Basic Functions Networks and Wavelet Networks”, in Proc. of ESANN 98, Bruges (B), April 1998, pp. 13–19.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Reyneri, L.M. (1999). Unification of supervised and unsupervised training. 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/BFb0098203
Download citation
DOI: https://doi.org/10.1007/BFb0098203
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