Issue
Dagstuhl Reports, Volume 10, Issue 4
-
Part of:
Volume:
Dagstuhl Reports, Volume 10
Journal: Dagstuhl Reports (DagRep)
Event
Dagstuhl Seminars 20372, 20382Publication Details
- published at: 2021-03-15
- Publisher: Schloss Dagstuhl – Leibniz-Zentrum für Informatik
- DBLP: db/journals/dagstuhl-reports/dagstuhl-reports10
Access Numbers
- Detailed Access Statistics available here
-
Total Document Accesses (updated on a weekly basis):
0PDF Downloads
Documents
No documents found matching your filter selection.
Document
Complete Issue
DagRep, Volume 10, Issue 4, September 2020, Complete Issue
Abstract
DagRep, Volume 10, Issue 4, April 2020, Complete Issue
Cite as
Dagstuhl Reports, Volume 10, Issue 4, pp. 1-44, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)
Copy BibTex To Clipboard
@Article{DagRep.10.4,
title = {{DagRep, Volume 10, Issue 4, September 2020, Complete Issue}},
pages = {1--44},
journal = {Dagstuhl Reports},
ISSN = {2192-5283},
year = {2021},
volume = {10},
number = {4},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/DagRep.10.4},
URN = {urn:nbn:de:0030-drops-137331},
doi = {10.4230/DagRep.10.4},
annote = {Keywords: DagRep, Volume 10, Issue 4, April 2020, Complete Issue}
}
Document
Front Matter
Dagstuhl Reports, Table of Contents, Volume 10, Issue 4, 2020
Abstract
Dagstuhl Reports, Table of Contents, Volume 10, Issue 4, 2020
Cite as
Dagstuhl Reports, Volume 10, Issue 4, pp. i-ii, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)
Copy BibTex To Clipboard
@Article{DagRep.10.4.i,
title = {{Dagstuhl Reports, Table of Contents, Volume 10, Issue 4, 2020}},
pages = {i--ii},
journal = {Dagstuhl Reports},
ISSN = {2192-5283},
year = {2021},
volume = {10},
number = {4},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/DagRep.10.4.i},
URN = {urn:nbn:de:0030-drops-137344},
doi = {10.4230/DagRep.10.4.i},
annote = {Keywords: Table of Contents, Frontmatter}
}
Document
Beyond Adaptation: Understanding Distributional Changes (Dagstuhl Seminar 20372)
Abstract
This report documents the program and the outcomes of Dagstuhl Seminar 20372 "Beyond Adaptation: Understanding Distributional Changes". It was centered around the aim to establish a better understanding of the causes, nature and consequences of distributional changes. Four key research questions were identified and discussed in during the seminar. These were the practical relevance of different scenarios and types of change, the modelling of change, the detection and measuring of change, and the adaptation to change.
The seminar brought together participants from several distinct communities in which parts of these questions are already studied, albeit in separate lines of research. These included data stream mining, where the focus is on concept drift detection and adaptation, transfer learning and domain adaptation in machine learning and algorithmic learning theory, change point detection in statistics, and the evolving and adaptive systems community. Therefore, this seminar contributed to stimulate research towards a thorough understanding of distributional changes.
Cite as
Georg Krempl, Vera Hofer, Geoffrey Webb, and Eyke Hüllermeier. Beyond Adaptation: Understanding Distributional Changes (Dagstuhl Seminar 20372). In Dagstuhl Reports, Volume 10, Issue 4, pp. 1-36, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)
Copy BibTex To Clipboard
@Article{krempl_et_al:DagRep.10.4.1,
author = {Krempl, Georg and Hofer, Vera and Webb, Geoffrey and H\"{u}llermeier, Eyke},
title = {{Beyond Adaptation: Understanding Distributional Changes (Dagstuhl Seminar 20372)}},
pages = {1--36},
journal = {Dagstuhl Reports},
ISSN = {2192-5283},
year = {2021},
volume = {10},
number = {4},
editor = {Krempl, Georg and Hofer, Vera and Webb, Geoffrey and H\"{u}llermeier, Eyke},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/DagRep.10.4.1},
URN = {urn:nbn:de:0030-drops-137359},
doi = {10.4230/DagRep.10.4.1},
annote = {Keywords: Statistical Machine Learning, Data Streams, Concept Drift, Non-Stationary Non-IID Data, Change Mining, Dagstuhl Seminar}
}
Document
Interactive Visualization for Fostering Trust in AI (Dagstuhl Seminar 20382)
Abstract
Artificial intelligence (AI), and in particular machine learning algorithms, are of increasing importance in many application areas but interpretability and understandability as well as responsibility, accountability, and fairness of the algorithms' results, all crucial for increasing the humans' trust into the systems, are still largely missing. Big industrial players, including Google, Microsoft, and Apple, have become aware of this gap and recently published their own guidelines for the use of AI in order to promote fairness, trust, interpretability, and other goals. Interactive visualization is one of the technologies that may help to increase trust in AI systems. During the seminar, we discussed the requirements for trustworthy AI systems as well as the technological possibilities provided by interactive visualizations to increase human trust in AI.
Cite as
Daniela Oelke, Daniel A. Keim, Polo Chau, and Alex Endert. Interactive Visualization for Fostering Trust in AI (Dagstuhl Seminar 20382). In Dagstuhl Reports, Volume 10, Issue 4, pp. 37-42, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)
Copy BibTex To Clipboard
@Article{oelke_et_al:DagRep.10.4.37,
author = {Oelke, Daniela and Keim, Daniel A. and Chau, Polo and Endert, Alex},
title = {{Interactive Visualization for Fostering Trust in AI (Dagstuhl Seminar 20382)}},
pages = {37--42},
journal = {Dagstuhl Reports},
ISSN = {2192-5283},
year = {2021},
volume = {10},
number = {4},
editor = {Oelke, Daniela and Keim, Daniel A. and Chau, Polo and Endert, Alex},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/DagRep.10.4.37},
URN = {urn:nbn:de:0030-drops-137360},
doi = {10.4230/DagRep.10.4.37},
annote = {Keywords: accountability, artificial intelligence, explainability, fairness, interactive visualization, machine learning, responsibility, trust, understandability}
}