Abstract
In this chapter we analyze the time varying analogues of the Ergodic learning algorithms presented in Chapter 2. These algorithms are obtained from algorithm (2.1) by letting the step length parameter θ to vary with time. The time-varying algorithms generate non-stationary Markov processes over the simplex SM. Our aim is to present different methods of asymptotic analysis of these time varying learning algorithms. In the interest of brevity we will only consider the case of M = 2, leaving the obvious extensions as exercises.
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
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1981 Springer-Verlag New York Inc.
About this chapter
Cite this chapter
Lakshmivarahan, S. (1981). Time Varying Learning Algorithms. In: Learning Algorithms Theory and Applications. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-5975-6_4
Download citation
DOI: https://doi.org/10.1007/978-1-4612-5975-6_4
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-90640-9
Online ISBN: 978-1-4612-5975-6
eBook Packages: Springer Book Archive