Varieties of Justification in Machine Learning
- 296 Downloads
Forms of justification for inductive machine learning techniques are discussed and classified into four types. This is done with a view to introduce some of these techniques and their justificatory guarantees to the attention of philosophers, and to initiate a discussion as to whether they must be treated separately or rather can be viewed consistently from within a single framework.
KeywordsInduction Guarantee Kernel methods Bayesian
The author thanks the Max Planck Society for supporting his research for this paper.
- Grünwald, P. (2007). The minimum description length principle. Cambridge: MIT Press.Google Scholar
- Harman, G., & Kulkarni, S. (2007). Reliable reasoning: Induction and statistical learning theory. Cambridge: MIT Press.Google Scholar
- LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., & Huang, F. (2006). A tutorial on energy-based learning. In G. Bakir, T. Hofman, B. Schölkopf, A. Smola & B. Taskar (Eds.), Predicting structured data. Cambridge: MIT Press.Google Scholar
- Minka, T. (2001). Empirical risk minimization is an incomplete inductive principle. http://www.research.microsoft.com/~minka/papers/minka-erm.pdf.
- Schölkopf, B., Tsuda, K., & Vert, J.-P. (eds.) (2004). Kernel methods in computational biology. Cambridge: MIT Press.Google Scholar
- Seeger, M. (2003). Bayesian Gaussian process models: PAC-Bayesian generalisation error bounds and sparse approximations. Dissertation, University of Edinburgh.Google Scholar
- Snoussi, H., & Mohammad-Djafari, A. (2002). Information geometry and Prior Selection. In C. J. Williams (Ed.), Proceedings of 22nd international workshop on Bayesian inference and maximum entropy methods in science and engineering (MaxEnt’02), pp. 307–327, Moscow, Idaho, USA, August 2002.Google Scholar
- Williamson, J. (2007). ‘Philosophies of probability: Objective bayesianism and its challenges. In A. Irvine (Ed.), Handbook of the philosophy of mathematics. Elsevier, Amsterdam. Handbook of the Philosophy of Science volume 4.Google Scholar