Navigation überspringen
Universitätsbibliothek Heidelberg
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Voß, Andreas [VerfasserIn]   i
 Mertens, Ulf K. [VerfasserIn]   i
 Radev, Stefan [VerfasserIn]   i
Titel:Learning the likelihood
Titelzusatz:using deepInference for the estimation of diffusion-model and Lévy flight parameters [dataset]
Verf.angabe:Andreas Voss, Ulf K. Mertens, Stefan T. Radev
Verlagsort:Heidelberg
Verlag:Universität
E-Jahr:2018
Jahr:2018-06-22
Umfang:1 Online-Ressource (5 Files)
Fussnoten:Gesehen am 02.07.2018 ; Deposit date: 2018-06-21 ; Grant information: Deutsche Forschungsgemeinschaft (DFG): Vo-1288-2
Abstract:In the corresponding paper, we use the recently develop DeepInference architecture as a general likelihood-free method to estimate parameters of cognitive models. DeepInference is a machine-learning algorithm based on the training of convolutional neural networks. In a first step, the network has to be trained with simulated data to learn the relation of parameters and data. Then, the trained network can be used to re-estimate parameters for real data. The efficiency and robustness of this approach was tested for two decision models based on continuous evidence accumulation. Study 1 investigated the recovery of parameters of the diffusion model, and Study 2 addressed the same question for a Lévy-Flight model. Results demonstrate that the machine-learning approach is superior to traditional multidimensional search algorithms that maximize the likelihood, both in terms of correlations of estimated parameters with true parameters and with regard to absolute deviations. The new approach also excels the maximum likelihood based search pertaining the robustness in the presence of contaminated data.
DOI:doi:10.11588/data/HY4OBJ
URL:Kostenfrei: Volltext ; Verlag: http://dx.doi.org/10.11588/data/HY4OBJ
 Kostenfrei: Volltext: https://heidata.uni-heidelberg.de/dataset.xhtml?persistentId=doi:10.11588/data/HY4OBJ
 DOI: https://doi.org/10.11588/data/HY4OBJ
Datenträger:Online-Ressource
Dokumenttyp:Forschungsdaten
 Datenbank
Sprache:eng
Sonstige Nr.:Grant number: Vo-1288-2
K10plus-PPN:1654144010
 
 
Lokale URL UB: Zum Volltext

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/68279537   QR-Code
zum Seitenanfang