Abstract
Cascade Correlation (Cascor) has proved to be a powerful method for training neural networks. Cascor, however, has been shown not to generalise well on regression and some classification problems. A new Cascade network algorithm employing Progressive RPROP (Casper), is proposed. Casper, like Cascor, is a constructive learning algorithm which builds cascade networks. Instead of using weight freezing and a correlation measure to install new neurons, however, Casper uses a variation of RPROP to train the whole network. Casper is shown to produce more compact networks, which generalise better than Cascor.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Adams, A., and Waugh, S. (1995) Function Evaluation and the Cascade-Correlation architecture In Proc. 1995 IEEE Int. Conf. Neural Networks. pp. 942–946.
Fahlman, S.E. (1988) Faster learning variations on backpropagation: An empirical study. In Proc. 1988 Connectionist Models Summer School. San Mateo, CA: Morgan Kauffman
Fahlman, S.E., and Lebiere, C. (1990) The cascade-correlation learning architecture. In Advances in Neural Information Processing II, Touretzky, Ed. San Mateo, CA: Morgan Kauffman, 1990, pp. 524–532.
Hwang, J., Lay, S., Maechler, R. And Martin, D. (1994) Regression Modeling in Back-Propagation and Projection Pursuit Learning. IEEE Trans. Neural Networks vol. 5, no. 3. pp. 342–353.
Hwang, J., You, S., Lay, S., and Jou, I. (1996) The Cascade-Correlation Learning: A Projection Pursuit Learning Perspective. IEEE Trans. Neural Networks vol. 7, no. 2. pp. 278–289.
Kwok, T., and Yeung, D. (1993) Experimental Analysis of Input Weight Freezing in Constructive Neural Networks. In Proc. 1993 IEEE Int. Conf. Neural Networks. pp. 511–516.
Riedmiller, M. and Braun, H. (1993) A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm. In: Ruspini, H., (Ed.) Proc. of the ICNN 93, San Francisco, pp. 586–591.
Riedmiller, M. (1994) Rprop — Description and Implementation Details, Technical Report, University of Karlsruhe.
Treadgold, N.K., and Gedeon, T.D. (1996) A Simulated Annealing Enhancement to Resilient Backpropagation. Proc. Int. Panel Conf. Soft and Intelligent Computing, Budapest pp. 293–298.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Treadgold, N.K., Gedeon, T.D. (1997). A cascade network algorithm employing Progressive RPROP. In: Mira, J., Moreno-DÃaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032532
Download citation
DOI: https://doi.org/10.1007/BFb0032532
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive