“Classifying memory traces in Judgments of Learning using Support-Vector Machines”
-
1
Maastricht University, Neuropsychology and psychopharmacology, Netherlands
Behavioural studies have demonstrated that monitoring the study process helps scholars regulate learning more efficiently. The mechanisms of monitoring one’s own knowledge are still under debate. It has been suggested that memory processes are involved, but only indirect proofs exist. The purpose of the present study is to provide supporting evidence of a key role of memory when students make Judgments of Learning (JOL), by looking at the underlying neural mechanisms with fMRI. We verified the hypothesis that immediate JOL are based on working memory networks, while delayed JOL involve long-term memory processes. A slow event-related design of a word pair paradigm was used to investigate brain activity of 5 healthy subjects during JOL and retrieval, both occurring at different time lags from encoding (8 seconds, 100 seconds, 24 hours). Multivariate pattern analyses, which have shown to be more sensitive at capturing distributed patterns of activity simultaneously measured, were used to classify BOLD signal of JOL and memory in each individual data set. Different classifiers were used and they successfully attributed immediate JOL to working memory, and delayed JOL to long-term memory with accuracies ranging from 85 to 90%. Our findings indicate that memory is a fundamental cue during JOL.
Keywords:
Memory,
Judgments of Learning,
fMRI,
multivariate analysis,
Learning
Conference:
Belgian Brain Council, Liège, Belgium, 27 Oct - 27 Oct, 2012.
Presentation Type:
Poster Presentation
Topic:
Other basic/clinical neurosciences topic
Citation:
Falbo
L and
Stiers
P
(2012). “Classifying memory traces in Judgments of Learning using Support-Vector Machines”.
Conference Abstract:
Belgian Brain Council.
doi: 10.3389/conf.fnhum.2012.210.00022
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
10 Sep 2012;
Published Online:
12 Sep 2012.
*
Correspondence:
Miss. Luciana Falbo, Maastricht University, Neuropsychology and psychopharmacology, Maastricht, Netherlands, luciana.falbo@maastrichtuniversity.nl