Premium
SLOW LEARNING
Author(s) -
Norman M. Frank
Publication year - 1968
Publication title -
british journal of mathematical and statistical psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.157
H-Index - 51
eISSN - 2044-8317
pISSN - 0007-1102
DOI - 10.1111/j.2044-8317.1968.tb00406.x
Subject(s) - variety (cybernetics) , computer science , mathematics , econometrics , machine learning , artificial intelligence
Learning will be slow if the quantity that represents the state of learning changes by small steps or with small probability on each experimental trial. Approximations to the distribution of this quantity for both types of slow learning are obtained. These approximations are applicable to a wide variety of models.