Empirical Inference

Varieties of Justification in Machine Learning

2009

Conference Paper

ei


The field of machine learning has flourished over the past couple of decades. With huge amounts of data available, efficient algorithms can learn to extrapolate from their training sets to become very accurate classifiers. For example, it is straightforward now to develop classifiers which achieve accuracies of around 99% on databases of handwritten digits. Now these algorithms have been devised by theorists who arrive at the problem of machine learning with a range of different philosophical outlooks on the subject of inductive reasoning. This has led to a wide range of theoretical rationales for their work. In this talk I shall classify the different forms of justification for inductive machine learning into four kinds, and make some comparisons between them. With little by way of theoretical knowledge to aid in the learning tasks, while the relevance of these justificatory approaches for the inductive reasoning of the natural sciences is questionable, certain issues surrounding the presuppositions of inductive reasoning are brought sharply into focus. In particular, Frequentist, Bayesian and MDL outlooks can be compared.

Author(s): Corfield, D.
Journal: Proceedings of Multiplicity and Unification in Statistics and Probability
Pages: 1-10
Year: 2009
Month: June
Day: 0

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: Multiplicity and Unification in Statistics and Probability
Event Place: Canterbury, UK

Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{5409,
  title = {Varieties of Justification in Machine Learning},
  author = {Corfield, D.},
  journal = {Proceedings of Multiplicity and Unification in Statistics and Probability},
  pages = {1-10},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = jun,
  year = {2009},
  doi = {},
  month_numeric = {6}
}