Download
s41598-020-61703-x.pdf 2,32MB
WeightNameValue
1000 Titel
  • Machine learning identifies the dynamics and influencing factors in an auditory category learning experiment
1000 Autor/in
  1. Abolfazli, Amir |
  2. Brechmann, André |
  3. Wolff, Susann |
  4. Spiliopoulou, Myra |
1000 Erscheinungsjahr 2020
1000 LeibnizOpen
1000 Publikationstyp
  1. Artikel |
1000 Online veröffentlicht
  • 2020-04-16
1000 Erschienen in
1000 Quellenangabe
  • 10(1):6548
1000 FRL-Sammlung
1000 Copyrightjahr
  • 2020
1000 Lizenz
1000 Verlagsversion
  • https://doi.org/10.1038/s41598-020-61703-x |
  • https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7162940/ |
1000 Ergänzendes Material
  • https://www.nature.com/articles/s41598-020-61703-x#Sec21 |
1000 Publikationsstatus
1000 Begutachtungsstatus
1000 Sprache der Publikation
1000 Abstract/Summary
  • Human learning is one of the main topics in psychology and cognitive neuroscience. The analysis of experimental data, e.g. from category learning experiments, is a major challenge due to confounding factors related to perceptual processing, feedback value, response selection, as well as inter-individual differences in learning progress due to differing strategies or skills. We use machine learning to investigate (Q1) how participants of an auditory category-learning experiment evolve towards learning, (Q2) how participant performance saturates and (Q3) how early we can differentiate whether a participant has learned the categories or not. We found that a Gaussian Mixture Model describes well the evolution of participant performance and serves as basis for identifying influencing factors of task configuration (Q1). We found early saturation trends (Q2) and that CatBoost, an advanced classification algorithm, can separate between participants who learned the categories and those who did not, well before the end of the learning session, without much degradation of separation quality (Q3). Our results show that machine learning can model participant dynamics, identify influencing factors of task design and performance trends. This will help to improve computational models of auditory category learning and define suitable time points for interventions into learning, e.g. by tutorial systems.
1000 Fächerklassifikation (DDC)
1000 Liste der Beteiligten
  1. https://frl.publisso.de/adhoc/uri/QWJvbGZhemxpLCBBbWly|https://orcid.org/0000-0003-3903-0840|https://frl.publisso.de/adhoc/uri/V29sZmYsIFN1c2Fubg==|https://frl.publisso.de/adhoc/uri/U3BpbGlvcG91bG91LCBNeXJh
1000 Label
1000 Förderer
  1. European Regional Development Fund |
  2. Deutsche Forschungsgemeinschaft |
  3. Leibniz-Gemeinschaft |
1000 Fördernummer
  1. ZS/2017/10/88783
  2. BR 2267/9-1
  3. -
1000 Förderprogramm
  1. -
  2. OSCAR "Opinion Stream Classification with Ensembles and Active Learners"
  3. Open Access Fund
1000 Dateien
1000 Förderung
  1. 1000 joinedFunding-child
    1000 Förderer European Regional Development Fund |
    1000 Förderprogramm -
    1000 Fördernummer ZS/2017/10/88783
  2. 1000 joinedFunding-child
    1000 Förderer Deutsche Forschungsgemeinschaft |
    1000 Förderprogramm OSCAR "Opinion Stream Classification with Ensembles and Active Learners"
    1000 Fördernummer BR 2267/9-1
  3. 1000 joinedFunding-child
    1000 Förderer Leibniz-Gemeinschaft |
    1000 Förderprogramm Open Access Fund
    1000 Fördernummer -
1000 Objektart article
1000 Beschrieben durch
1000 @id frl:6420640.rdf
1000 Erstellt am 2020-05-06T10:22:21.315+0200
1000 Erstellt von 242
1000 beschreibt frl:6420640
1000 Bearbeitet von 122
1000 Zuletzt bearbeitet 2020-05-14T11:32:54.311+0200
1000 Objekt bearb. Thu May 14 11:32:42 CEST 2020
1000 Vgl. frl:6420640
1000 Oai Id
  1. oai:frl.publisso.de:frl:6420640 |
1000 Sichtbarkeit Metadaten public
1000 Sichtbarkeit Daten public
1000 Gegenstand von

View source