Abstract
Visualization of MLP error surfaces helps to understand the influence of network structure and training data on neural learning dynamics. PCA is used to determine two orthogonal directions that capture almost all variance in the weight space. 3-dimensional plots show many aspects of the original error surfaces.
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
Kordos, M., Duch, W.: Multilayer Perceptron Trained with Numerical Gradient. In: Int. Conf. on Artificial Neural Networks, Istanbul, June 2003, pp. 106–109 (2003)
Kordos, M., Duch, W.: Search-based Training for Logical Rule Extraction by Multilayer Perceptron. In: Int. Conf. on Artificial Neural Networks, Istanbul, June 2003, pp. 86–89 (2003)
Haykin, S.: Neural networks: a comprehensive foundations. MacMillian Publishing, New York (1994)
Mertz, C.J., Murphy, P.M.: UCI repository of machine learning databases, http://www.ics.uci.edu/pub/machine-learning-data-bases
Denker, J., et al.: Large automatic learning, rule extraction and generalization. Complex Systems 1, 887–922 (1987)
Sussmann, H.J.: Uniqueness of the weights for minimal feedforward nets with a given inputoutput map. Neural Networks 5, 589–593 (1992)
Gallagher, M.R.: Multi-layer Perceptron Error Surfaces: Visualization, Structure and Modeling, PhD Thesis, University of Queensland (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kordos, M., Duch, W. (2004). On Some Factors Influencing MLP Error Surface. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds) Artificial Intelligence and Soft Computing - ICAISC 2004. ICAISC 2004. Lecture Notes in Computer Science(), vol 3070. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24844-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-540-24844-6_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22123-4
Online ISBN: 978-3-540-24844-6
eBook Packages: Springer Book Archive