Abstract
Constructive cascade algorithms are powerful methods for training feedforward neural networks with automation of the task of specifying the size and topology of network to use. A series of empirical studies were performed to examine the effect of imposing constraints on constructive cascade neural network architectures. Building a priori knowledge of the task into the network gives better generalisation performance. We introduce our Local Feature Constructive Cascade (LoCC) and Symmetry Local Feature Constructive Cascade (SymLoCC) algorithms, and show them to have good generalisation and network construction properties on face recognition tasks.
This is a preview of subscription content, log in via an institution to check access.
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
Kwok, T.-Y., Yeung, D.-Y.: Constructive Algorithms for Structure Learning in Feedforward Neural Networks for Regression Problems. IEEE Trans. on Neural Networks 8, 630–645 (1997)
LeCun, Y.: Generalization and Network Design Strategies. Technical report, Dept. of Computer Science, University of Toronto (1989)
Grudin, M.A.: On Internal Representations in Face Recognition Systems. Pattern Recognition 33, 1161–1177 (2000)
Treadgold, N.K., Gedeon, T.D.: Exploring Architecture Variations in Constructive Cascade Networks. In: IEEE Int. Jt. Conf. on Neural Networks, pp. 343–348 (1998)
Khoo, S.: Application of Shared Weight Neural Networks in Image Classification. Honours Thesis, Dept. Computer Science, Australian National University (2008)
Fahlman, S., Liebiere, C.: The Cascade-Correlation Learning Architecture. Technical report, School of Computer Science, Carnegie Mellon University (1990)
Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose. IEEE Trans. on Pattern Analysis and Machine Intelligence 23, 643–660 (2001)
Cover, T.M., Hart, P.E.: Nearest Neighbor Pattern Classification. IEEE Trans. on Information Theory IT-13, 21–27 (1967)
Nguyen, D., Widrow, B.: Improving the Learning Speed of 2-Layer Neural Networks by Choosing Initial Values of the Adaptive Weights. In: IEEE Int. Jt. Conf. on Neural Networks, pp. 21–26 (1990)
Riedmiller, M., Braun, H.: A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm. In: IEEE Int. Conf. on Neural Networks, pp. 586–591 (1993)
Treadgold, N.K., Gedeon, T.D.: Increased Generalization through Selective Decay in a Constructive Cascade Network. In: Proc. 1998 IEEE Int. Conf. on Systems, Man, and Cybernetics, pp. 4465–4469 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Khoo, S., Gedeon, T. (2009). Generalisation Performance vs. Architecture Variations in Constructive Cascade Networks. In: Köppen, M., Kasabov, N., Coghill, G. (eds) Advances in Neuro-Information Processing. ICONIP 2008. Lecture Notes in Computer Science, vol 5507. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03040-6_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-03040-6_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03039-0
Online ISBN: 978-3-642-03040-6
eBook Packages: Computer ScienceComputer Science (R0)