Abstract
We present a new incremental procedure for supervised learning with noisy data. Each step consists in adding to the current network a new unit 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. First experimental results point out the efficacy of this new incremental scheme. Current works deal with theoretical analysis and practical refinements of the algorithm.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
D.R. Reilly, L.N. Cooper, C. Elbaum. 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, 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 Cun, J. Denker, S. Solla. Optimal Brain Damage,Advances in Neural Information Processing vol. 2, pp. 598–605, 1990.
M. Cottrell, B. Girard, Y. Girard, 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 inIEEE Trans. on Neural Networks.
R. Reed. Pruning algorithm — a survey,IEEE Trans. on Neural Networks vol. 4, nℴ5, pp. 740–747.
C. Louis, B. Gittler, 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, C. Jutten. A comparison of two weight pruning methods,2nd European Symposium on Artificial Neural Networks (Brussels), pp. 147–152, 1994.
T. Ameniya.Advanced Econometrics, Basil Blackwell, 1986.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Jutten, C., Chentouf, R. A new scheme for incremental learning. Neural Process Lett 2, 1–4 (1995). https://doi.org/10.1007/BF02312374
Issue Date:
DOI: https://doi.org/10.1007/BF02312374