Saved in:
Bibliographic Details
Main Authors: Klaß, Andreas, Lorenz, Sven M., Lauer-Schmaltz, Martin W., Rügamer, David, Bischl, Bernd, Mutschler, Christopher, Ott, Felix
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2206.08640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913532372582400
author Klaß, Andreas
Lorenz, Sven M.
Lauer-Schmaltz, Martin W.
Rügamer, David
Bischl, Bernd
Mutschler, Christopher
Ott, Felix
author_facet Klaß, Andreas
Lorenz, Sven M.
Lauer-Schmaltz, Martin W.
Rügamer, David
Bischl, Bernd
Mutschler, Christopher
Ott, Felix
contents For many applications, analyzing the uncertainty of a machine learning model is indispensable. While research of uncertainty quantification (UQ) techniques is very advanced for computer vision applications, UQ methods for spatio-temporal data are less studied. In this paper, we focus on models for online handwriting recognition, one particular type of spatio-temporal data. The data is observed from a sensor-enhanced pen with the goal to classify written characters. We conduct a broad evaluation of aleatoric (data) and epistemic (model) UQ based on two prominent techniques for Bayesian inference, Stochastic Weight Averaging-Gaussian (SWAG) and Deep Ensembles. Next to a better understanding of the model, UQ techniques can detect out-of-distribution data and domain shifts when combining right-handed and left-handed writers (an underrepresented group).
format Preprint
id arxiv_https___arxiv_org_abs_2206_08640
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift
Klaß, Andreas
Lorenz, Sven M.
Lauer-Schmaltz, Martin W.
Rügamer, David
Bischl, Bernd
Mutschler, Christopher
Ott, Felix
Computer Vision and Pattern Recognition
Artificial Intelligence
62F15
H.1.1
For many applications, analyzing the uncertainty of a machine learning model is indispensable. While research of uncertainty quantification (UQ) techniques is very advanced for computer vision applications, UQ methods for spatio-temporal data are less studied. In this paper, we focus on models for online handwriting recognition, one particular type of spatio-temporal data. The data is observed from a sensor-enhanced pen with the goal to classify written characters. We conduct a broad evaluation of aleatoric (data) and epistemic (model) UQ based on two prominent techniques for Bayesian inference, Stochastic Weight Averaging-Gaussian (SWAG) and Deep Ensembles. Next to a better understanding of the model, UQ techniques can detect out-of-distribution data and domain shifts when combining right-handed and left-handed writers (an underrepresented group).
title Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift
topic Computer Vision and Pattern Recognition
Artificial Intelligence
62F15
H.1.1
url https://arxiv.org/abs/2206.08640