Abstract
In this Section we extend the techniques of devising algorithms of a priori guaranteed learning properties. More distinctly, we derive conditions under which various modifications of the kernel-sequence W do not influence the asymptotic learning properties, and the behavior of the learning process may also be kept under control within finite training periods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1975 Springer-Verlag Wien
About this chapter
Cite this chapter
Csibi, S. (1975). Approximations. In: Stochastic Processes with Learning Properties. International Centre for Mechanical Sciences, vol 84. Springer, Vienna. https://doi.org/10.1007/978-3-7091-3006-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-7091-3006-3_8
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-81337-9
Online ISBN: 978-3-7091-3006-3
eBook Packages: Springer Book Archive