Skip to main content
SpringerLink
Log in
SpringerLink
Log in

Induction

  • Reference work entry
Encyclopedia of Machine Learning

  • 161 Accesses

Definition

Induction is the process of inferring a general rule from a collection of observed instances. Sometimes it is used more generally to refer to any inference from premises to conclusion where the truth of the conclusion does not follow deductively from the premises, but where the premises provide evidence for the conclusion. In this more general sense, induction includes abduction where facts rather than rules are inferred. (The word “induction” also denotes a different, entirely deductive form of argument used in mathematics.)

Theory

Hume’s Problem of Induction

The problem of induction was famously set out by the great Scottish empiricist philosopher David Hume (1711–1776), although he did not actually use the word “induction” in this context. With characteristic bluntness, he argued that:

there can be no demonstrative arguments to prove that those instances of which we have had no experience resemble those of which we have had experience (Hume, 1739, Part 3, Section 6).

...

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Recommended Reading

  • Bacchus, F., Grove, A., Halpern, J. Y., & Koller, D. (1996). From statistical knowledge bases to degrees of belief. Artificial Intelligence, 87(1–2), 75–143.

    MathSciNet  Google Scholar 

  • Carnap, R. (1950). Logical foundations of probability. Chicago: University of Chicago Press.

    MATH  Google Scholar 

  • Cussens, J. (1996). Deduction, induction and probabilistic support. Synthese, 108(1), 1–10.

    MATH  MathSciNet  Google Scholar 

  • Howson, C., & Urbach, P. (1989). Scientific reasoning: The Bayesian approach. La Salle, IL: Open Court.

    Google Scholar 

  • Hume, D. (1739). A treatise of human nature, book one (Anonymously published).

    Google Scholar 

  • Hume, D. (1740). An abstract of a treatise of human nature (Anonymously published as a pamphlet). London.

    Google Scholar 

  • Lakatos, I. (1970). Falsification and the methodology of scientific research programmes. In I. Lakatos & A. Musgrave (Eds.), Criticism and the growth of knowledge (pp. 91–196). Cambridge, MA: Cambridge University Press.

    Google Scholar 

  • Popper, K. R. (1959). The logic of scientific discovery. London: Hutchinson (Translation of Logik der Forschung, 1934).

    Google Scholar 

  • Popper, K. R., & Miller, D. (1984). The impossibility of inductive probability. Nature, 310, 434.

    Google Scholar 

  • Popper, K. R., & Miller, D. (1987). Why probabilistic support is not inductive. Philosophical Transactions of the Royal Society of London, 321, 569–591.

    MATH  MathSciNet  Google Scholar 

  • Wolpert, D. H. (1992). On the connection between in-sample testing and generalization error. Complex Systems, 6, 47–94.

    MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

    Authors
    1. James Cussens
      View author publications

      You can also search for this author in PubMed Google Scholar

    Editor information

    Editors and Affiliations

    1. School of Computer Science and Engineering, University of New South Wales, Sydney, Australia, 2052

      Claude Sammut

    2. Faculty of Information Technology, Clayton School of Information Technology, Monash University, P.O. Box 63, Victoria, Australia, 3800

      Geoffrey I. Webb

    Rights and permissions

    Reprints and permissions

    Copyright information

    © 2011 Springer Science+Business Media, LLC

    About this entry

    Cite this entry

    Cussens, J. (2011). Induction. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_388

    Download citation

    Publish with us

    Policies and ethics

    Search

    Navigation