Abstract
Meta-learning can be seen as alternating the construction of configuration of learning machines for validation, scheduling of such tasks and the meta-knowledge collection.
This article presents a few modifications of complexity measures and their application in advising to scheduling test tasks—validation tasks of learning machines in meta-learning process. Additionally some comments about their optimality in context of meta-learning are presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Brazdil, P., Giraud-Carrier, C., Soares, C., Vilalta, R.: Metalearning: Applications to Data Mining. Springer (2009)
Solomonoff, R.: A preliminary report on a general theory of inductive inference. Technical Report V-131, Cambridge, Ma.: Zator Co. (1960)
Solomonoff, R.: A formal theory of inductive inference part i. Information and Control 7(1), 1–22 (1964)
Solomonoff, R.: A formal theory of inductive inference part ii. Information and Control 7(2), 224–254 (1964)
Kolmogorov, A.N.: Three approaches to the quantitative definition of information. Prob. Inf. Trans. 1, 1–7 (1965)
Li, M., Vitányi, P.: An Introduction to Kolmogorov Complexity and Its Applications. Text and Monographs in Computer Science. Springer (1993)
Jankowski, N.: Applications of Levin’s universal optimal search algorithm. In: Kącki, E. (ed.) System Modeling Control 1995, vol. 3, pp. 34–40. Polish Society of Medical Informatics, Łódź (May 1995)
Levin, L.A.: Universal sequential search problems. Problems of Information Transmission 9 (1973), translated from Problemy Peredachi Informatsii (Russian)
Merz, C.J., Murphy, P.M.: UCI repository of machine learning databases (1998), http://www.ics.uci.edu/~mlearn/MLRepository.html
Grąbczewski, K., Jankowski, N.: Saving time and memory in computational intelligence system with machine unification and task spooling. Knowledge-Based Systems 24(5), 570–588 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Jankowski, N. (2013). Complexity Measures for Meta-learning and Their Optimality. In: Dowe, D.L. (eds) Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence. Lecture Notes in Computer Science, vol 7070. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-44958-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-44958-1_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-44957-4
Online ISBN: 978-3-642-44958-1
eBook Packages: Computer ScienceComputer Science (R0)