Abstract
This chapter investigates the regression models and methods for machine learning in engineering computations, from both non-Bayesian and Bayesian perspectives. The non-Bayesian regression models, including the least square regression, ridge regression, and support vector regression, equipped or not equipped with kernel trick, are first examined as they share the same principle, which is to find an element in the parametrically indexed hypothesis set by minimizing specific empirical loss functions. The Bayesian regression models are then investigated from the views of parametric space, and then functional space, all of which aim at assigning probabilistic beliefs on the elements of the hypothesis set using Bayesian inference. It is highlighted that, with specific assumptions, the Bayesian models provide measures of the prediction errors for unobserved points. This feature allows to develop a unique learning skill, i.e. active learning, which aims at devising optimal design strategies for minimizing the number of simulator calls, especially when each call is computationally cumbersome. This is shown to be effective when applied to cutting-edge research on Bayesian numerical analysis such as Bayesian cubature and Bayesian reliability assessment examined in this chapter. Both theoretical details and numerical examples are presented for examining each method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Au SK, Beck JL (2001) Probabilistic Eng Mech 16(4):263
Bichon BJ, Eldred MS, Swiler LP, Mahadevan S, McFarland JM (2008) AIAA J 46(10):2459
Briol FX, Oates CJ, Girolami M, Osborne MA, Sejdinovic D et al (2019) Stat Sci 34(1):1
Chen Y, Hosseini B, Owhadi H, Stuart AM (2021) J Comput Phys 447:110668
Cockayne J, Oates CJ, Sullivan TJ, Girolami M (2019) SIAM Rev 61(4):756
Dang C, Wei P, Song J, Beer M (2021) ASCE-ASME J Risk Uncertain Eng Systems Part A: Civ Eng 7(4):4021054
Echard B, Gayton N, Lemaire M (2011) Struct Saf 33(2):145
Hennig P, Osborne MA, Kersting HP (2022) Probabilistic numerics Cambridge University Press
Huang D, Allen TT, Notz WI, Zeng N (2006) J Glob Optim 34(3):441
Johnson RA, Wichern DW (2007) Applied multivariate statistical analysis, 6th edn
Mohri M, Rostamizadeh A, Talwalkar A (2018) Foundations of machine learning, 2nd edn
Nocedal J, Wright SJ (2006) Springer,
Perdikaris P, Raissi M, Damianou A, Lawrence ND, Karniadakis GE (2017) Proc R Soc A: Math Phys Eng Sci 473(2198):20160751
Rasmussen CE, Ghahramani Z (2003) Adv Neural Inf Process Syst 15:505
Rasmussen CE, Williams C (2006) MIT Press 39:40
Schueller GI, Pradlwarter HJ, Koutsourelakis PS (2004) Probabilistic Eng Mech 19(4):463
Song J, Wei P, Valdebenito M, Beer M (2021) Mech Syst Signal Process 147:107113
Theodoridis S (2015) Machine learning: a bayesian and optimization perspective
Wang J, Cockayne J, Chkrebtii OA, Sullivan TJ, Oates CJ (2021) Stat Comput 31(5):1
Wei P, Tang C, Yang Y (2019) Proc Inst Mech Engineers Part O: J Risk Reliab 233(6):943
Wei P, Zhang X, Beer M (2020) Comput Methods Appl Mech Eng 365:113035
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Wei, P., Beer, M. (2023). Regression Models for Machine Learning. In: Rabczuk, T., Bathe, KJ. (eds) Machine Learning in Modeling and Simulation. Computational Methods in Engineering & the Sciences. Springer, Cham. https://doi.org/10.1007/978-3-031-36644-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-36644-4_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36643-7
Online ISBN: 978-3-031-36644-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)