Skip to main content

Inductive learning with corroboration

Watson, Phil (1999) Inductive learning with corroboration. Technical report. (KAR id:21824)


The basis of inductive learning is the process of generating and refuting hypotheses. Natural approaches to this form of learning assume that a data item that causes refutation of one hypothesis opens the way for the introduction of a new (for now unrefuted) hypothesis, and so such data items have attracted the most attention. Data items that do not cause refutation of the current hypothesis have until now been largely ignored in these processes, but in practical learning situations they play the key role of em corroborating those hypotheses that they do not refute. We formalise a version of K.R. Popper's concept of em degree of corroboration for inductive inference and utilise it in an inductive learning procedure which has the natural behaviour of outputting the most strongly corroborated (non-refuted) hypothesis at each stage. We demonstrate its utility by providing characterisations of several of the commonest identification types. In many cases we believe that these characterisations make the relationships between these types clearer than the standard characterisations. The idea of learning with corroboration therefore provides a unifying approach for the field.

Item Type: Monograph (Technical report)
Uncontrolled keywords: Degree of corroboration, inductive inference, philosophy of science
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming,
Divisions: Faculties > Sciences > School of Computing > Theoretical Computing Group
Depositing User: Mark Wheadon
Date Deposited: 03 Sep 2009 09:28 UTC
Last Modified: 28 May 2019 14:01 UTC
Resource URI: (The current URI for this page, for reference purposes)
  • Depositors only (login required):


Downloads per month over past year