Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A Formal Framework for Knowledge Acquisition: Going beyond Machine Learning
Stockholms universitet, Naturvetenskapliga fakulteten, Matematiska institutionen.ORCID-id: 0000-0003-2767-8818
Rekke forfattare: 32022 (engelsk)Inngår i: Entropy, E-ISSN 1099-4300, Vol. 24, nr 10, artikkel-id 1469Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Philosophers frequently define knowledge as justified, true belief. We built a mathematical framework that makes it possible to define learning (increasing number of true beliefs) and knowledge of an agent in precise ways, by phrasing belief in terms of epistemic probabilities, defined from Bayes’ rule. The degree of true belief is quantified by means of active information I+: a comparison between the degree of belief of the agent and a completely ignorant person. Learning has occurred when either the agent’s strength of belief in a true proposition has increased in comparison with the ignorant person (I+>0), or the strength of belief in a false proposition has decreased (I+<0). Knowledge additionally requires that learning occurs for the right reason, and in this context we introduce a framework of parallel worlds that correspond to parameters of a statistical model. This makes it possible to interpret learning as a hypothesis test for such a model, whereas knowledge acquisition additionally requires estimation of a true world parameter. Our framework of learning and knowledge acquisition is a hybrid between frequentism and Bayesianism. It can be generalized to a sequential setting, where information and data are updated over time. The theory is illustrated using examples of coin tossing, historical and future events, replication of studies, and causal inference. It can also be used to pinpoint shortcomings of machine learning, where typically learning rather than knowledge acquisition is in focus.

sted, utgiver, år, opplag, sider
2022. Vol. 24, nr 10, artikkel-id 1469
Emneord [en]
active information, Bayes' rule, counterfactuals, epistemic probability, learning, justified true belief, knowledge acquisition, replication studies
HSV kategori
Identifikatorer
URN: urn:nbn:se:su:diva-211039DOI: 10.3390/e24101469ISI: 000872645400001Scopus ID: 2-s2.0-85140609692OAI: oai:DiVA.org:su-211039DiVA, id: diva2:1709698
Tilgjengelig fra: 2022-11-09 Laget: 2022-11-09 Sist oppdatert: 2023-03-28bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Hössjer, Ola

Søk i DiVA

Av forfatter/redaktør
Hössjer, Ola
Av organisasjonen
I samme tidsskrift
Entropy

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 45 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf