Improving the repeatability of two-rate model parameter estimations by using autoencoder networks

The adaptive changes elicited in visuomotor adaptation experiments are usually well explained at group level by two-rate models (Smith et al., 2006), but parameters fitted to individuals show considerable variance. Data cleaning can mitigate this problem, but the assumption of smoothness can be prob...

Full description

Saved in:
Bibliographic Details
Published in:Progress in brain research Vol. 249; p. 189
Main Authors: Ozdemir, Murat C, Eggert, Thomas, Straube, Andreas
Format: Journal Article
Language:English
Japanese
Published: Netherlands 2019
Subjects:
Adaptation, Physiological - physiology
Adult
Humans
Models, Biological
Motor Activity - physiology
Neural Networks, Computer
Psychomotor Performance - physiology
Visual Perception - physiology
Human
Two-rate models
Visuomotor adaptation
Autoencoder
Data cleaning
ISSN:1875-7855, 1875-7855
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The adaptive changes elicited in visuomotor adaptation experiments are usually well explained at group level by two-rate models (Smith et al., 2006), but parameters fitted to individuals show considerable variance. Data cleaning can mitigate this problem, but the assumption of smoothness can be problematic due to fast adaptive changes with discontinuous derivatives. In this paper, we collected time-series data from an experimental paradigm involving repeated training and investigated the effect of various cleaning methods, including an autoencoder network (AE), on the parameter estimation. We compared changes in the fitted parameters across different methods and across training repetitions. The results suggest that AE performed best overall, without introducing an underestimation bias on b like moving average or piecewise polynomials, and that it reduced the within-subject variance overall and especially that of the fast retention rate a by >50%.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1875-7855
1875-7855
DOI:10.1016/bs.pbr.2019.04.035