Abstract
We recently proposed a new incremental procedure for supervised learning with noisy data. Each step consists in adding to the current network a new unit (or small 2- or 3-neuron networks) which is trained to learn the error of the network. The incremental step is repeated until the error of the current network can be considered as a noise. The stopping criterion is very simple and can be directly deduced from a statistical test on the estimated parameters of the new unit. In this paper, we develop experimental comparison between few alternatives of the incremental algorithm and classic backpropagation algorithm, according to convergence, speed of convergence and optimal number of neurons. Experimental results point out the efficacy of this new incremental scheme especially to avoid spurious minima and to design a network with a well-suited size. The number of basic operations is also decreased and gives an average gain on convergence speed of about 20%.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
D.R. Reilly, L.N. Cooper and C. Erlbaum. A Neural Model for Category Learning, Biological Cybernetics vol. 45, pp. 35–41, 1982.
E. Alpaydin. Grow and Learn: An Incremental Method for Category Learning, Proc. Int. Neural Network Conf. (Paris) vol. II, pp. 761–764, 1990.
M. Mézard and J.P Nadal. Learning in Feedforward Layered Networks: the Tiling Algorithm, J. Phys. A: Maths. Gen. vol. 22, pp. 2191–2203, 1989.
M. Frean. The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks, Neural computation vol. 2, pp. 198–209, 1990.
Y. Le Cnn, J. Denker and S. Solla. Optimal Brain Damage, Advances in Neural Information Processing vol. 2, pp. 598–605, 1990.
M. Cottrell, B. Girard, Y. Girard and M. Mangeas. Time Series And Neural Network: A Statistical Method For Weight Elimination, 1st European Symposium on Artificial Neural Networks (Brussels), pp. 157–164, 1993.
M. Cottrell, B. Girard, Y. Girard, M. Mangeas, C. Muller. Neural Modeling For Time Series: A Statistical Stepwise Method For Weight Elimination. To appear in IEEE Trans. on Neural Networks.
R. Reed. Pruning Algorithm — A Survey, IEEE Trans. on Neural Networks vol. 4, n°5, pp. 740–747.
J. Sietsma, R.J.F. Dow. Creating artificial networks that generalize. Neural Networks, vol. 4, n°l, pp. 67–79, 1991.
C. Louis, B. Gittler and F. Moutarde. Un algorithme de dimensionnement pour atteindre un réseau d'architecture minimale, Neural Networks and their applications (Marseille), December 15–16, 1994.
O. Fambon and C. Jutten. A Comparison of Two Weight Pruning Methods, European Symposium on Artificial Neural Networks, (Brussels), pp. 147–152, 1994.
C. Jutten. and R. Chentouf. A New Scheme for Incremental Learning, Accepted for Neural Processing Letters (Brussels), 1995.
T. Ameniya. Advanced Econometrics. Basil Blackwell, 1986.
A. Benveniste, M. Métivier, P. Priouret. Adaptive Algorithms and Stochastic Approximations. Springer-Verlag, Berlin, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chentouf, R., Jutten, C. (1995). Incremental learning with a stopping criterion experimental results. 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_218
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_218
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