Abstract
A common theme in answering the question of how distinct concepts are represented in neural networks is to associate meaning to the activity of an individual, or set of neurons. While such models may provide an explanation of how reasoning may occur, they rarely suggest how structures come to exist, often relying on some form of the innateness conjecture. This paper addresses the issue of concept formation by using the principle of structural risk minimization during network construction. This paper describes two related methods for incrementally constructing networks from smaller network architectures. The methods are applied to an image prediction problem that provides a sufficiently difficult learning task, while allowing both quantitive and qualitative analysis of performance. Experiments suggest that incrementally introducing structure during learning in a principled manner can assist in overcoming the bias/variance problem as, for the given problem, the methods show no sign of over-fitting after prolonged training.
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
Anthony, M., Biggs, N.: Computational Learning Theory. An Introduction. Cambridge Tracts inTheoretical Computer Science, vol. 30. Cambridge University Press, Cambridge (1992)
Fahlman, S., Lebiere, C.: The cascade-correlation learning architecture. In: Lippman, R., Moody, J., Touretzky, D. (eds.) Advances in Neural Information Processing Systems, vol. 3, pp. 190–196. Morgan-Kaufmann, San Mateo (1990)
Gallant, S.: Perceptron based learning algorithms. IEEE Transactions on Neural Networks 1(2), 179–191 (1990)
Geman, S., Bienenstock, E., Doursat, R.: Neural networks and the bias/variance dilemma. Neural Computation 4, 1–58 (1992)
Nadal, J.P.: Study of a growth algorithm for a feedforward network. International Journal of Neural Systems 1(1), 55–59 (1989)
Quinlan, J.: Bagging boosting and c4.5. In: Proceedings of the Thirtenth National Conference on Artificial Intelligence, pp. 725–730 (1996)
Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The rprop algorithm. In: Proceedings of the IEEE International Conference on Neural Networks, San Francisco, pp. 586–591 (1993)
Schapire, R., Fruend, Y., Bartlett, P., Lee, W.S.: Boosting the margin: A new explanation for the effectiveness of voting methods. The Annuals of Statistics 26(5), 1651–1686 (1998)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995) ISBN 0 387 94559 8
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hayward, R. (2003). Using Images to Compare Two Constructive Network Techniques. In: Gedeon, T.(.D., Fung, L.C.C. (eds) AI 2003: Advances in Artificial Intelligence. AI 2003. Lecture Notes in Computer Science(), vol 2903. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24581-0_46
Download citation
DOI: https://doi.org/10.1007/978-3-540-24581-0_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20646-0
Online ISBN: 978-3-540-24581-0
eBook Packages: Springer Book Archive