Pregled bibliografske jedinice broj: 982183
How Gruesome are the No-free-lunch Theorems for Machine Learning?
How Gruesome are the No-free-lunch Theorems for Machine Learning? // Croatian journal of philosophy, XVIII (2018), 54; 479-489 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 982183 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
How Gruesome are the No-free-lunch Theorems for
Machine Learning?
Autori
Lauc, Davor
Izvornik
Croatian journal of philosophy (1333-1108) XVIII
(2018), 54;
479-489
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
Induction ; the problem of ; No-free-lunch theorems ; The new riddle of induction
Sažetak
No-free-lunch theorems are important theoretical result in the fi elds of machine learning and artifi cial intelligence. Researchers in this fi elds often claim that the theorems are based on Hume’s argument about induction and represent a formalisation of the argument. This paper argues that this is erroneous but that the theorems correspond to and formalise Goodman’s new riddle of induction. To demonstrate the correspondence among the theorems and Goodman’s argument, a formalisation of the latter in the spirit of the former is sketched.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Filozofija
POVEZANOST RADA
Ustanove:
Filozofski fakultet, Zagreb,
Sveučilište u Zagrebu
Profili:
Davor Lauc
(autor)
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Arts & Humanities Citation Index (A&HCI)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus
