Search: (WFRF:(Rao J. Sunil)) > A Formal Framework ...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 03409naa a2200469 4500 | |
001 | oai:DiVA.org:su-211039 | |
003 | SwePub | |
008 | 221109s2022 | |||||||||||000 ||eng| | |
024 | 7 | a https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-2110392 URI |
024 | 7 | a https://doi.org/10.3390/e241014692 DOI |
040 | a (SwePub)su | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a art2 swepub-publicationtype |
100 | 1 | a Hössjer, Ola,d 1964-u Stockholms universitet,Matematiska institutionen4 aut0 (Swepub:su)ohssj |
245 | 1 0 | a A Formal Framework for Knowledge Acquisition :b Going beyond Machine Learning |
264 | c 2022-10-14 | |
264 | 1 | b MDPI AG,c 2022 |
338 | a print2 rdacarrier | |
520 | a 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. | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskap0 (SwePub)1022 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciences0 (SwePub)1022 hsv//eng |
650 | 7 | a NATURVETENSKAPx Matematik0 (SwePub)1012 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Mathematics0 (SwePub)1012 hsv//eng |
650 | 7 | a HUMANIORAx Filosofi, etik och religion0 (SwePub)6032 hsv//swe |
650 | 7 | a HUMANITIESx Philosophy, Ethics and Religion0 (SwePub)6032 hsv//eng |
653 | a active information | |
653 | a Bayes' rule | |
653 | a counterfactuals | |
653 | a epistemic probability | |
653 | a learning | |
653 | a justified true belief | |
653 | a knowledge acquisition | |
653 | a replication studies | |
700 | 1 | a Díaz-Pachón, Daniel Andrés4 aut |
700 | 1 | a Rao, J. Sunil4 aut |
710 | 2 | a Stockholms universitetb Matematiska institutionen4 org |
773 | 0 | t Entropyd : MDPI AGg 24:10q 24:10x 1099-4300 |
856 | 4 | u https://doi.org/10.3390/e24101469y Fulltext |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-211039 |
856 | 4 8 | u https://doi.org/10.3390/e24101469 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.