Statistical Machine Learning and the Logic of Scientific Discovery.
One important problem in the philosophy of science is whether there can be a normative theory of discovery, as opposed to a normative theory of justification. Although the possibility of developing a logic of scientific discovery has been often doubted by philosophers, it is particularly interesting...
| Published in: | Iris: European Journal of Philosophy & Public Debate Vol. 1; no. 2; pp. 375 - 389 |
|---|---|
| Main Author: | |
| Format: | Article |
| Published: |
Firenze University Press
Oct2009
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=47365071&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 47365071 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 20363257 90DI jtl: Iris: European Journal of Philosophy & Public Debate issn: 20363257 maglogo: N pubinfo: dt: Oct2009 vid: 1 iid: 2 pid: 32694 pub: Firenze University Press artinfo: ui: 47365071 ppf: 375 ppct: 14 formats: fmt: @attributes: type: P size: 355KB tig: atl: Statistical Machine Learning and the Logic of Scientific Discovery. aug: au: Freno, Antonino su: Machine learning Philosophy of science Normative theory (Communication) Computer science Stochastic learning models Induction (Logic) Justification (Theory of knowledge) Markov random fields Scientific discoveries sug: subj: Machine learning Philosophy of science Normative theory (Communication) Computer science Stochastic learning models Induction (Logic) Justification (Theory of knowledge) Markov random fields Scientific discoveries ab: One important problem in the philosophy of science is whether there can be a normative theory of discovery, as opposed to a normative theory of justification. Although the possibility of developing a logic of scientific discovery has been often doubted by philosophers, it is particularly interesting to consider how the basic insights of a normative theory of discovery have been turned into an effective research program in computer science, namely the research field of machine learning. In this paper, I introduce some current research on statistical models to a philosophical audience. In particular, I will stress those features of statistical models that make them plausible computational counterparts of scientific theories. After noticing how these models allow for the main kinds of inference that are a trademark of scientific theories, I will focus on the problem of learning statistical models from data. The analysis will show how machine learning is casting new light on traditional problems in the philosophy of science. More precisely, I will explore the implications of some results in statistical learning with respect to the role of simplicity in theory choice and to the role of scalability (as a formal property of induction) in making scientific discovery effective. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Copyright of Iris: European Journal of Philosophy & Public Debate is the property of Firenze University Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. item: Iris: European Journal of Philosophy & Public Debate holder: Firenze University Press dt: @attributes: year: 2009 holdings: @attributes: islocal: N |
|---|