Abstract
In this chapter we formulate and prove convergence theorems for most of the credit assignment schemes introduced in Chapter 3. The presentation style is quite uniform: in every case a theorem is stated, which has the general form: “the credit of the best model converges to one as time goes to infinity”; what is meant by “best model” in every case is explained and various remarks are made regarding the algorithm, the conditions necessary for convergence and so on. The actual proofs are presented in several Appendices at the end of the chapter.
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
© 1998 Springer Science+Business Media New York
About this chapter
Cite this chapter
Petridis, V., Kehagias, A. (1998). Mathematical Analysis. In: Predictive Modular Neural Networks. The Springer International Series in Engineering and Computer Science, vol 466. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5555-1_4
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5555-1_4
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7540-1
Online ISBN: 978-1-4615-5555-1
eBook Packages: Springer Book Archive