Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
Medientyp:
E-Artikel
Titel:
Simple Models in Complex Worlds: Occam’s Razor and Statistical Learning Theory
Beteiligte:
Bargagli Stoffi, Falco J.;
Cevolani, Gustavo;
Gnecco, Giorgio
Erschienen:
Springer Science and Business Media LLC, 2022
Erschienen in:Minds and Machines
Sprache:
Englisch
DOI:
10.1007/s11023-022-09592-z
ISSN:
0924-6495;
1572-8641
Entstehung:
Anmerkungen:
Beschreibung:
<jats:title>Abstract</jats:title><jats:p>The idea that “simplicity is a sign of truth”, and the related “Occam’s razor” principle, stating that, all other things being equal, simpler models should be preferred to more complex ones, have been long discussed in philosophy and science. We explore these ideas in the context of supervised machine learning, namely the branch of artificial intelligence that studies algorithms which balance simplicity and accuracy in order to effectively learn about the features of the underlying domain. Focusing on statistical learning theory, we show that situations exist for which a preference for simpler models (as modeled through the addition of a regularization term in the learning problem) provably slows down, instead of favoring, the supervised learning process. Our results shed new light on the relations between simplicity and truth approximation, which are briefly discussed in the context of both machine learning and the philosophy of science.</jats:p>