Vorlesen

Research Seminar Series in Statistics and Mathematics

Wirtschaftsuniversität Wien, Departments 4 D4.4.00809:00 - 10:30

Art Vortrag/Diskussion
SpracheEnglish
Vortragende/rHarald Baayen (Department of Linguistics, University of Tübingen)
Veranstalter Institut für Statistik und Mathematik
Kontakt katrin.artner@wu.ac.at

Harald Baayen (Department of Linguistics, University of Tübingen) about "Wide learning in language modeling"

The Institute for Statistics and Mathematics (Department of Finance, Accounting and Statistics) cordially invites everyone interested to attend the talks in our Research Seminar Series, where internationally renowned scholars from leading universities present and discuss their (working) papers.
No registration required.

The list of talks for the summer term 2019 is available via the following link: https://www.wu.ac.at/en/statmath/resseminar

Abstract:
Convolutional neural networks are widely and successfully used in natural language processing. However, it turns out that there are tasks in which learning with ‘wide’ networks, i.e., simple networks with just an input and an output layer and very large numbers of units, can be surprisingly successful when carefully chosen features (based on domain knowledge) are used. I will illustrate finding for three case studies: French baboons learning to discriminate between English words and pseudowords, human auditory word recognition, and the computational modeling of inflectional morphology with what amounts to multivariate multiple regression.



zurück zur Übersicht