Abstract
In this paper the learning capabilities of a class of neural networks named Stochastic Approximate Identity Neural Networks (SAINNs) have been analyzed. In particular these networks are able to approximate a large class of stochastic processes from the knowledge of their covariance function.
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
Karhunen, K.: Uber lineare Methoden in der Wahrscheinlicherechnung. Ann. Acad. Sci. Fennicae, Ser. A. Math. Phys. 37, 3–79 (1947)
Turchetti, C., Conti, M., Crippa, P., Orcioni, S.: On the Approximation of Stochastic Processes by Approximate Identity Neural Networks. IEEE Trans. Neural Networks 9(6), 1069–1085 (1998)
Belli, M.R., Conti, M., Crippa, P., Turchetti, C.: Artificial Neural Networks as Approximators of Stochastic Processes. Neural Networks 12(4-5), 647–658 (1999)
Doob, J.L.: Stochastic Processes. J. Wiley & Sons, New York (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Crippa, P., Turchetti, C. (2003). Learning of SAINNs from Covariance Function: Historical Learning. In: Palade, V., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2003. Lecture Notes in Computer Science(), vol 2773. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45224-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-45224-9_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40803-1
Online ISBN: 978-3-540-45224-9
eBook Packages: Springer Book Archive