Abstract
One significant source of roundoff error in backpropagation networks is the calculation of derivatives of unit outputs with respect to their total inputs. The roundoff error can lead result in high relative error in derivatives, and in particular, derivatives being calculated to be zero when in fact they are small but non-zero. This roundoff error is easily avoided with a simple programming trick which has a small memory overhead (one or two extra floating point numbers per unit) and an insignificant computational overhead.
Previously published in: Orr, G.B. and Müller, K.-R. (Eds.): LNCS 1524, ISBN 978-3-540-65311-0 (1998).
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
Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press (1995)
Fahlman, S.E.: Fast-learning variations on back-propagation: An empirical study. In: Touretzky, D., Hinton, G., Sejnowski, T. (eds.) Proceedings of the 1988 Connectionist Models Summer School, pp. 38–51. Morgan Kaufmann, San Mateo (1989)
Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press (1995)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 318–362. MIT Press, Cambridge (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Plate, T. (2012). Avoiding Roundoff Error in Backpropagating Derivatives. In: Montavon, G., Orr, G.B., Müller, KR. (eds) Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science, vol 7700. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35289-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-35289-8_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35288-1
Online ISBN: 978-3-642-35289-8
eBook Packages: Computer ScienceComputer Science (R0)