Testability and Ockham’s Razor: How Formal and Statistical Learning Theory Converge in the New Riddle of Induction [Book Review]

Journal of Philosophical Logic 38 (5):471 - 489 (2009)
  Copy   BIBTEX


Nelson Goodman’s new riddle of induction forcefully illustrates a challenge that must be confronted by any adequate theory of inductive inference: provide some basis for choosing among alternative hypotheses that fit past data but make divergent predictions. One response to this challenge is to distinguish among alternatives by means of some epistemically significant characteristic beyond fit with the data. Statistical learning theory takes this approach by showing how a concept similar to Popper’s notion of degrees of testability is linked to minimizing expected predictive error. In contrast, formal learning theory appeals to Ockham’s razor, which it justifies by reference to the goal of enhancing efficient convergence to the truth. In this essay, I show that, despite their differences, statistical and formal learning theory yield precisely the same result for a class of inductive problems that I call strongly VC ordered , of which Goodman’s riddle is just one example.



    Upload a copy of this work     Papers currently archived: 93,098

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles


Added to PP

177 (#114,381)

6 months
26 (#116,274)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

References found in this work

The logic of scientific discovery.Karl Raimund Popper - 1934 - New York: Routledge. Edited by Hutchinson Publishing Group.
Fact, Fiction, and Forecast.Nelson Goodman - 1973 - Cambridge: Harvard University Press.
The Logic of Scientific Discovery.K. Popper - 1959 - British Journal for the Philosophy of Science 10 (37):55-57.
Fact, Fiction, and Forecast.Nelson Goodman - 1955 - Philosophy 31 (118):268-269.

View all 20 references / Add more references