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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
C. Bishop. Neural Networks for Pattern Recognition. Oxford University Press, 1995.
S.E. Fahlman. Fast-learning variations on back-propagation: An empirical study. In D. Touretzky, G. Hinton, and T. Sejnowski, editors, Proceedings of the 1988 Connectionist Models Summer School, pages 38–51, San Mateo, 1989. Morgan Kaufmann.
B.D. Ripley. Pattern Recognition and Neural Networks. Cambridge University Press, 1995.
D. E. Rumelhart, G. E. Hinton, and Williams R. J. Learning internal representations by error propagation. In Parallel distributed processing: Explorations in the micro structure of cognition, volume 1, pages 318–362. MIT Press, Cambridge,MA, 1986.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Plate, T. (1998). Avoiding roundoff error in backpropagating derivatives. In: Orr, G.B., Müller, KR. (eds) Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science, vol 1524. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49430-8_12
Download citation
DOI: https://doi.org/10.1007/3-540-49430-8_12
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65311-0
Online ISBN: 978-3-540-49430-0
eBook Packages: Springer Book Archive