Abstract
The paper deals with the problem of finding an estimation of supervisor set and content of machine learning block. We propose a construction of a probability distribution of the learning set using the empirical risk functional defined by Vapnik and applying a new dual dynamic programming ideas to formulate a new optimization problem. As a consequence we state and prove a verification theorem for an approximate probability distribution defining the approximation of the supervisor set.
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
References
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (2000). https://doi.org/10.1007/978-1-4757-3264-1
Vapnik, V., Izmailov, R.: Knowledge transfer in SVM and neural networks. Ann. Math Artif. Intell. 81(1), 3–19 (2017)
Vapnik, V., Braga, I., Izmailov, R.: Constructive setting for problems of density ratio estimation. Stat. Anal. Data Min. 8(3), 137–146 (2015)
Nowakowski, A.: The dual dynamic programming. Proc. Am. Math. Soc. 116, 1089–1096 (1992)
Nowakowski, A.: \(\varepsilon \)-value function and dynamic programming. J. Optim. Theory Appl. 138, 85–93 (2008)
Galewska, E., Nowakowski, A.: A dual dynamic programming for multidimensional elliptic optimal control problems. Numer. Funct. Anal. Optim. 27, 279–289 (2006)
Nowakowski, A., Sokolowski, J.: On dual dynamic programming in shape control. Commun. Pure Appl. Anal. 11, 2473–2485 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Kosmatka, K., Nowakowski, A. (2019). Estimating Supervisor Set Using Machine Learning and Optimal Control. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science(), vol 11507. Springer, Cham. https://doi.org/10.1007/978-3-030-20518-8_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-20518-8_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20517-1
Online ISBN: 978-3-030-20518-8
eBook Packages: Computer ScienceComputer Science (R0)