Abstract
In this chapter we are concerned with constraints under which a broad class of machine learning procedures, governed by iteration rules with memory, converge. More distinctly, we assume iteration rules with weak (or just finite) memory with respect to previous data and previously proposed estimates. Procedures of this sort offer rich possibilities to find convergent learning algorithms with powerful processing steps, and reduce in this way the time necessary for learning. We prove, in what follows, relations of interest in devising such sort of iteration rules. Use of these results, e.g., for modifying convergent learning algorithms heuristically, while retaining their convergence, and other related topics are subjects we consider in Chapter 5.
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). Iteration Rules with Weak Memory. 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_4
Download citation
DOI: https://doi.org/10.1007/978-3-7091-3006-3_4
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-81337-9
Online ISBN: 978-3-7091-3006-3
eBook Packages: Springer Book Archive