Abstract
The conditions for learnability of a task by a computer algorithm provide guidance for understanding their performance and guidance for selecting the appropriate learning algorithm for a particular task. In this chapter, we present the two main theoretical frameworks—probably approximately correct (PAC) and Vapnik–Chervonenkis (VC) dimension—which allow us to answer questions such as which learning process we should select, what is the learning capacity of the algorithm selected, and under which conditions is successful learning possible or impossible. Practical methods for selecting proper model complexity are presented using techniques based on information theory and statistical resampling.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fisher RA. Statistical methods for research workers. Edinburgh: Oliver and Boyd; 1925.
Fisher RA. The design of experiments. Edinburgh: Oliver and Boyde; 1935.
Vapnik VN. The nature of statistical learning theory. New York: Springer; 1995.
Mitchell TM. Machine learning. New York: McGraw-Hill; 1997.
Berry MJA, Linoff G. Data mining techniques: for marketing, sales, and customer relationship management. 2nd ed. Indianapolis: Wiley Pub; 2004.
Nilsson NJ, Nilsson NJ. The mathematical foundations of learning machines. San Mateo: Morgan Kaufmann; 1990.
Guyon I, Elissee A. An introduction to variable and feature selection. J Mach Learn Res. 2003;3:1157–82.
Dawson LA, Biersack M, Lockwood G, Eisbruch A, Lawrence TS, Ten Haken RK. Use of principal component analysis to evaluate the partial organ tolerance of normal tissues to radiation. Int J Radiat Oncol Biol Phys. 2005;62:829–37.
Kennedy R, Lee Y, Van Roy B, Reed CD, Lippman RP. Solving data mining problems through pattern recognition. Upper Saddle River, NJ: Prentice Hall; 1998.
Härdle W, Simar L. Applied multivariate statistical analysis. Berlin/New York: Springer; 2003.
Guyon I, Weston J, Barnhill S, Vapnik V. Gene selection for cancer classification using support vector machines. Mach Learn. 2002;46:389–422.
Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning: data mining, inference, and prediction: with 200 full-color illustrations. New York: Springer; 2001.
Deasy JO, El Naqa I. Image-based modeling of normal tissue complication probability for radiation therapy. Cancer Treat Res. 2008;139:215–56.
Burnham KP, Anderson DR. Model selection and multimodal inference: a practical information-theoretic approach. 2nd ed. New York: Springer; 2002.
Efron B, Tibshirani R. An introduction to the bootstrap. New York: Chapman & Hall; 1993.
El Naqa I, Bradley JD, Lindsay PE, Blanco AI, Vicic M, Hope AJ, et al. Multi-variable modeling of radiotherapy outcomes including dose-volume and clinical factors. Int J Radiat Oncol Biol Phys. 2006;64:1275–86.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
El Naqa, I. (2015). Computational Learning Theory. In: El Naqa, I., Li, R., Murphy, M. (eds) Machine Learning in Radiation Oncology. Springer, Cham. https://doi.org/10.1007/978-3-319-18305-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-18305-3_2
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-18304-6
Online ISBN: 978-3-319-18305-3
eBook Packages: MedicineMedicine (R0)