Abstract
This article introduces a simple filter to the basic implementation of the feed forward artificial neural network. The filter chooses the frequency at which to use training data based on reliability of the provided training example. We posit that the inclusion of this filter will improve the effectiveness of the neural network during actual usage. However, implementation and testing shows that filtering training data for reliability does not significantly improve the effectiveness of the neural network.
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
References
Rosenblatt, L., Papert, S.: Perceptrons. MIT, Cambridge (1969)
Rumelhart, D., Hinton, G., Williams, R.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Moniz, K., Yuan, Y. (2014). Filtering Training Data When Training Feed-Forward Artificial Neural Network. In: Yuan, Y., Wu, X., Lu, Y. (eds) Trustworthy Computing and Services. ISCTCS 2013. Communications in Computer and Information Science, vol 426. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-43908-1_28
Download citation
DOI: https://doi.org/10.1007/978-3-662-43908-1_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-43907-4
Online ISBN: 978-3-662-43908-1
eBook Packages: Computer ScienceComputer Science (R0)