MapView: Graphical Data Representation for Active Learning

Eva Weigl; Alexander Walch; Ulrich Neissl; Pauline Meyer-Heye; Wolfgang Heidl; Thomas Radauer; Edwin Lughofer; Christian Eitzinger

MapView: Graphical Data Representation for Active Learning

Eva Weigl, Alexander Walch, Ulrich Neissl, Pauline Meyer-Heye, Wolfgang Heidl, Thomas Radauer, Edwin Lughofer, Christian Eitzinger

Institute for Mathematical Methods in Medicine and Data Based Modeling

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

Active learning facilitates the training of classifiers by selectively querying the user in order to gain insights on unlabeled data samples. Until recently, the user had limited abilities to interact with an active learning system: A sub-selection was presented by the system and every sample within had to be annotated. We propose an alternative and graphical solution to active learning called MapView, where the user may profit from a different interpretation of the underlying data. Experiments underline the usability and advantages of our approach during the training of a classifier from scratch

Original language	English
Title of host publication	Workshop on Active Learning: Applications, Foundations and Emerging Trends (iKNOW Conference 2016)
Place of Publication	Graz, Austria
Pages	3-8
Number of pages	6
Publication status	Published - 2016

Publication series

Name	Proceedings of the iKnow Conference 2016

Fields of science

101 Mathematics
101013 Mathematical logic
101024 Probability theory
102001 Artificial intelligence
102003 Image processing
102019 Machine learning
603109 Logic
202027 Mechatronics

JKU Focus areas

Computation in Informatics and Mathematics
Mechatronics and Information Processing
Nano-, Bio- and Polymer-Systems: From Structure to Function

Cite this

@inproceedings{2d77306f1aca4c8ba617aee44708c31e,

title = "MapView: Graphical Data Representation for Active Learning",

abstract = "Active learning facilitates the training of classifiers by selectively querying the user in order to gain insights on unlabeled data samples. Until recently, the user had limited abilities to interact with an active learning system: A sub-selection was presented by the system and every sample within had to be annotated. We propose an alternative and graphical solution to active learning called MapView, where the user may profit from a different interpretation of the underlying data. Experiments underline the usability and advantages of our approach during the training of a classifier from scratch",

author = "Eva Weigl and Alexander Walch and Ulrich Neissl and Pauline Meyer-Heye and Wolfgang Heidl and Thomas Radauer and Edwin Lughofer and Christian Eitzinger",

year = "2016",

language = "English",

series = "Proceedings of the iKnow Conference 2016",

pages = "3--8",

booktitle = "Workshop on Active Learning: Applications, Foundations and Emerging Trends (iKNOW Conference 2016)",

}

MapView: Graphical Data Representation for Active Learning. / Weigl, Eva; Walch, Alexander; Neissl, Ulrich et al.
Workshop on Active Learning: Applications, Foundations and Emerging Trends (iKNOW Conference 2016). Graz, Austria, 2016. p. 3-8 (Proceedings of the iKnow Conference 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

TY - GEN

T1 - MapView: Graphical Data Representation for Active Learning

AU - Weigl, Eva

AU - Walch, Alexander

AU - Neissl, Ulrich

AU - Meyer-Heye, Pauline

AU - Heidl, Wolfgang

AU - Radauer, Thomas

AU - Lughofer, Edwin

AU - Eitzinger, Christian

PY - 2016

Y1 - 2016

N2 - Active learning facilitates the training of classifiers by selectively querying the user in order to gain insights on unlabeled data samples. Until recently, the user had limited abilities to interact with an active learning system: A sub-selection was presented by the system and every sample within had to be annotated. We propose an alternative and graphical solution to active learning called MapView, where the user may profit from a different interpretation of the underlying data. Experiments underline the usability and advantages of our approach during the training of a classifier from scratch

AB - Active learning facilitates the training of classifiers by selectively querying the user in order to gain insights on unlabeled data samples. Until recently, the user had limited abilities to interact with an active learning system: A sub-selection was presented by the system and every sample within had to be annotated. We propose an alternative and graphical solution to active learning called MapView, where the user may profit from a different interpretation of the underlying data. Experiments underline the usability and advantages of our approach during the training of a classifier from scratch

UR - https://www.scopus.com/pages/publications/84996995713

M3 - Conference proceedings

T3 - Proceedings of the iKnow Conference 2016

SP - 3

EP - 8

BT - Workshop on Active Learning: Applications, Foundations and Emerging Trends (iKNOW Conference 2016)

CY - Graz, Austria

ER -

MapView: Graphical Data Representation for Active Learning

Abstract

Publication series

Fields of science

JKU Focus areas

Other files and links

mvControl

Cite this

MapView: Graphical Data Representation for Active Learning

Abstract

Publication series

Fields of science

JKU Focus areas

Other files and links

Projects

mvControl

Cite this