Search Results

Documents authored by van Harmelen, Frank

Document
DOI: 10.4230/DagRep.14.5.1
Generalization by People and Machines (Dagstuhl Seminar 24192)

Authors: Barbara Hammer, Filip Ilievski, Sascha Saralajew, and Frank van Harmelen

Published in: Dagstuhl Reports, Volume 14, Issue 5 (2024)

Abstract
Today’s AI systems are powerful to the extent that they have largely entered the mainstream and divided the world between those who believe AI will solve all our problems and those who fear that AI will be destructive for humanity. Meanwhile, trusting AI is very difficult given its lack of robustness to novel situations, consistency of its outputs, and interpretability of its reasoning process. Building trustworthy AI requires a paradigm shift from the current oversimplified practice of crafting accuracy-driven models to a human-centric design that can enhance human ability on manageable tasks, or enable humans and AIs to solve complex tasks together that are difficult for either separately. At the core of this problem is the unrivaled human generalization and abstraction ability. While today’s AI is able to provide a response to any input, its ability to transfer knowledge to novel situations is still limited by oversimplification practices, as manifested by tasks that involve pragmatics, agent goals, and understanding of narrative structures. As there are currently no venues that allow cross-disciplinary research on the topic of reliable AI generalization, this discrepancy is problematic and requires dedicated efforts to bring in one place generalization experts from different fields within AI, but also with Cognitive Science. This Dagstuhl Seminar thus provided a unique opportunity for discussing the discrepancy between human and AI generalization mechanisms and crafting a vision on how to align the two streams in a compelling and promising way that combines the strengths of both. To ensure an effective seminar, we brought together cross-disciplinary perspectives across computer and cognitive science fields. Our participants included experts in Interpretable Machine Learning, Neuro-Symbolic Reasoning, Explainable AI, Commonsense Reasoning, Case-based Reasoning, Analogy, Cognitive Science, and Human-AI Teaming. Specifically, the seminar participants focused on the following questions: How can cognitive mechanisms in people be used to inspire generalization in AI? What Machine Learning methods hold the promise to enable such reasoning mechanisms? What is the role of data and knowledge engineering for AI and human generalization? How can we design and model human-AI teams that can benefit from their complementary generalization capabilities? How can we evaluate generalization in humans and AI in a satisfactory manner?
Cite as

Barbara Hammer, Filip Ilievski, Sascha Saralajew, and Frank van Harmelen. Generalization by People and Machines (Dagstuhl Seminar 24192). In Dagstuhl Reports, Volume 14, Issue 5, pp. 1-11, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@Article{hammer_et_al:DagRep.14.5.1,
  author =	{Hammer, Barbara and Ilievski, Filip and Saralajew, Sascha and van Harmelen, Frank},
  title =	{{Generalization by People and Machines (Dagstuhl Seminar 24192)}},
  pages =	{1--11},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2024},
  volume =	{14},
  number =	{5},
  editor =	{Hammer, Barbara and Ilievski, Filip and Saralajew, Sascha and van Harmelen, Frank},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.14.5.1},
  URN =		{urn:nbn:de:0030-drops-222682},
  doi =		{10.4230/DagRep.14.5.1},
  annote =	{Keywords: Abstraction, Cognitive Science, Generalization, Human-AI Teaming, Interpretable Machine Learning, Neuro-Symbolic AI}
}
Document
DOI: 10.4230/DagRep.12.6.112
Human-Centered Artificial Intelligence (Dagstuhl Seminar 22262)

Authors: Wendy E. Mackay, John Shawe-Taylor, and Frank van Harmelen

Published in: Dagstuhl Reports, Volume 12, Issue 6 (2023)

Abstract
This report documents the program and the outcomes of Dagstuhl Perspectives Workshop 22262 "Human-Centered Artificial Intelligence". The goal of this Dagstuhl Perspectives Workshops is to provide the scientific and technological foundations for designing and deploying hybrid human-centered AI systems that work in partnership with human beings and that enhance human capabilities rather than replace human intelligence. Fundamentally new solutions are needed for core research problems in AI and human-computer interaction (HCI), especially to help people understand actions recommended or performed by AI systems and to facilitate meaningful interaction between humans and AI systems. Specific challenges include: learning complex world models; building effective and explainable machine learning systems; developing human-controllable intelligent systems; adapting AI systems to dynamic, open-ended real-world environments (in particular robots and autonomous systems); achieving in-depth understanding of humans and complex social contexts; and enabling self-reflection within AI systems.
Cite as

Wendy E. Mackay, John Shawe-Taylor, and Frank van Harmelen. Human-Centered Artificial Intelligence (Dagstuhl Seminar 22262). In Dagstuhl Reports, Volume 12, Issue 6, pp. 112-117, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@Article{mackay_et_al:DagRep.12.6.112,
  author =	{Mackay, Wendy E. and Shawe-Taylor, John and van Harmelen, Frank},
  title =	{{Human-Centered Artificial Intelligence (Dagstuhl Seminar 22262)}},
  pages =	{112--117},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2023},
  volume =	{12},
  number =	{6},
  editor =	{Mackay, Wendy E. and Shawe-Taylor, John and van Harmelen, Frank},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.12.6.112},
  URN =		{urn:nbn:de:0030-drops-174579},
  doi =		{10.4230/DagRep.12.6.112},
  annote =	{Keywords: Human-centered Artificial Intelligence, Human-Computer Interaction, Hybrid Intelligence}
}
Document
DOI: 10.4230/DagRep.11.8.11
Structure and Learning (Dagstuhl Seminar 21362)

Authors: Tiansi Dong, Achim Rettinger, Jie Tang, Barbara Tversky, and Frank van Harmelen

Published in: Dagstuhl Reports, Volume 11, Issue 8 (2022)

Abstract
This report documents the program and the outcomes of Dagstuhl Seminar 21362 "Structure and Learning", held from September 5 to 10, 2021. Structure and learning are among the most prominent topics in Artificial Intelligence (AI) today. Integrating symbolic and numeric inference was set as one of the next open AI problems at the Townhall meeting "A 20 Year Roadmap for AI" at AAAI 2019. In this Dagstuhl seminar, we discussed related problems from an interdiscplinary perspective, in particular, Cognitive Science, Cognitive Psychology, Physics, Computational Humor, Linguistic, Machine Learning, and AI. This report overviews presentations and working groups during the seminar, and lists two open problems.
Cite as

Tiansi Dong, Achim Rettinger, Jie Tang, Barbara Tversky, and Frank van Harmelen. Structure and Learning (Dagstuhl Seminar 21362). In Dagstuhl Reports, Volume 11, Issue 8, pp. 11-34, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@Article{dong_et_al:DagRep.11.8.11,
  author =	{Dong, Tiansi and Rettinger, Achim and Tang, Jie and Tversky, Barbara and van Harmelen, Frank},
  title =	{{Structure and Learning (Dagstuhl Seminar 21362)}},
  pages =	{11--34},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2022},
  volume =	{11},
  number =	{8},
  editor =	{Dong, Tiansi and Rettinger, Achim and Tang, Jie and Tversky, Barbara and van Harmelen, Frank},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.11.8.11},
  URN =		{urn:nbn:de:0030-drops-157670},
  doi =		{10.4230/DagRep.11.8.11},
  annote =	{Keywords: Knowledge graph, Machine learning, Neural-symbol unification}
}
Document
DOI: 10.4230/DagRep.2.5.93
Cognitive Approaches for the Semantic Web (Dagstuhl Seminar 12221)

Authors: Dedre Gentner, Frank van Harmelen, Pascal Hitzler, Krzysztof Janowicz, and Kai-Uwe Kühnberger

Published in: Dagstuhl Reports, Volume 2, Issue 5 (2012)

Abstract
A major focus in the design of Semantic Web ontology languages used to be on finding a suitable balance between the expressivity of the language and the tractability of reasoning services defined over this language. This focus mirrors the original vision of a Web composed of machine readable and understandable data. Similarly to the classical Web a few years ago, the attention is recently shifting towards a user-centric vision of the Semantic Web. Essentially, the information stored on the Web is from and for humans. This new focus is not only reflected in the fast growing Linked Data Web but also in the increasing influence of research from cognitive science, human computer interaction, and machine-learning. Cognitive aspects emerge as an essential ingredient for future work on knowledge acquisition, representation, reasoning, and interactions on the Semantic Web. Visual interfaces have to support semantic-based retrieval and at the same time hide the complexity of the underlying reasoning machinery from the user. Analogical and similarity-based reasoning should assist users in browsing and navigating through the rapidly increasing amount of information. Instead of pre-defined conceptualizations of the world, the selection and conceptualization of relevant information has to be tailored to the user's context on-the-fly. This involves work on ontology modularization and context-awareness, but also approaches from ecological psychology such as affordance theory which also plays an increasing role in robotics and AI. During the Dagstuhl Seminar 12221 we discussed the most promising ways to move forward on the vision of bringing findings from cognitive science to the Semantic Web, and to create synergies between the different areas of research. While the seminar focused on the use of cognitive engineering for a user-centric Semantic Web, it also discussed the reverse direction, i.e., how can the Semantic Web work on knowledge representation and reasoning feed back to the cognitive science community.
Cite as

Dedre Gentner, Frank van Harmelen, Pascal Hitzler, Krzysztof Janowicz, and Kai-Uwe Kühnberger. Cognitive Approaches for the Semantic Web (Dagstuhl Seminar 12221). In Dagstuhl Reports, Volume 2, Issue 5, pp. 93-116, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2012)

Copy BibTex To Clipboard

@Article{gentner_et_al:DagRep.2.5.93,
  author =	{Gentner, Dedre and van Harmelen, Frank and Hitzler, Pascal and Janowicz, Krzysztof and K\"{u}hnberger, Kai-Uwe},
  title =	{{Cognitive Approaches for the Semantic Web (Dagstuhl Seminar 12221)}},
  pages =	{93--116},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2012},
  volume =	{2},
  number =	{5},
  editor =	{Gentner, Dedre and van Harmelen, Frank and Hitzler, Pascal and Janowicz, Krzysztof and K\"{u}hnberger, Kai-Uwe},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.2.5.93},
  URN =		{urn:nbn:de:0030-drops-37115},
  doi =		{10.4230/DagRep.2.5.93},
  annote =	{Keywords: Cognitive methods, Semantic Web, Analogy and similarity-based reasoning, Semantic heterogeneity and context, Symbol grounding, Emerging semantics, Comonsense reasoning}
}
Document
DOI: 10.4230/DagSemProc.10042.4
Towards Expressive Stream Reasoning

Authors: Heiner Stuckenschmidt, Stefano Ceri, Emanuele Della Valle, and Frank van Harmelen

Published in: Dagstuhl Seminar Proceedings, Volume 10042, Semantic Challenges in Sensor Networks (2010)

Abstract
Stream Data processing has become a popular topic in database research addressing the challenge of efficiently answering queries over continuous data streams. Meanwhile data streams have become more and more important as a basis for higher level decision processes that require complex reasoning over data streams and rich background knowledge. In previous work the foundation for complex reasoning over streams and background knowledge was laid by introducing technologies for wrapping and querying streams in the RDF data format and by supporting simple forms of reasoning in terms of incremental view maintenance. In this paper, we discuss how this existing technologies should be extended toward richer forms of reasoning using Sensor Networks as a motivating example.
Cite as

Heiner Stuckenschmidt, Stefano Ceri, Emanuele Della Valle, and Frank van Harmelen. Towards Expressive Stream Reasoning. In Semantic Challenges in Sensor Networks. Dagstuhl Seminar Proceedings, Volume 10042, pp. 1-14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2010)

Copy BibTex To Clipboard

@InProceedings{stuckenschmidt_et_al:DagSemProc.10042.4,
  author =	{Stuckenschmidt, Heiner and Ceri, Stefano and Della Valle, Emanuele and van Harmelen, Frank},
  title =	{{Towards Expressive Stream Reasoning}},
  booktitle =	{Semantic Challenges in Sensor Networks},
  pages =	{1--14},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2010},
  volume =	{10042},
  editor =	{Karl Aberer and Avigdor Gal and Manfred Hauswirth and Kai-Uwe Sattler and Amit P. Sheth},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.10042.4},
  URN =		{urn:nbn:de:0030-drops-25555},
  doi =		{10.4230/DagSemProc.10042.4},
  annote =	{Keywords: Streaming Data, Reasoning, C-SPARQL, Sensor Networks}
}
Document
DOI: 10.4230/DagSemProc.09161.1
09161 Abstracts Collection – Generalization of spatial information

Authors: Sébastien Mustière, Monika Sester, Frank van Harmelen, and Peter van Oosterom

Published in: Dagstuhl Seminar Proceedings, Volume 9161, Generalization of spatial information (2009)

Abstract
From 13.04. to 17.04.2009, the Dagstuhl Seminar 09161 ``Generalization of spatial information '' was held in Schloss Dagstuhl~--~Leibniz Center for Informatics. During the seminar, several participants presented their current research, and ongoing work and open problems were discussed. Abstracts of the presentations given during the seminar as well as abstracts of seminar results and ideas are put together in this paper. The first section describes the seminar topics and goals in general. Links to extended abstracts or full papers are provided, if available.
Cite as

Sébastien Mustière, Monika Sester, Frank van Harmelen, and Peter van Oosterom. 09161 Abstracts Collection – Generalization of spatial information. In Generalization of spatial information. Dagstuhl Seminar Proceedings, Volume 9161, pp. 1-18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2009)

Copy BibTex To Clipboard

@InProceedings{mustiere_et_al:DagSemProc.09161.1,
  author =	{Musti\`{e}re, S\'{e}bastien and Sester, Monika and van Harmelen, Frank and van Oosterom, Peter},
  title =	{{09161 Abstracts Collection – Generalization of spatial information }},
  booktitle =	{Generalization of spatial information},
  pages =	{1--18},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{9161},
  editor =	{S\'{e}bastien Musti\`{e}re and Monika Sester and Frank van Harmelen and Peter van Oosterom},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.09161.1},
  URN =		{urn:nbn:de:0030-drops-21506},
  doi =		{10.4230/DagSemProc.09161.1},
  annote =	{Keywords: Spatial information, generalization, aggregation, web services, formal semantics, geo-ontology, user context, constraint specification, progressive data transfer, computational geometry, cartography, mobile systems}
}
Document
DOI: 10.4230/DagSemProc.09161.2
09161 Summary – Generalization of spatial information

Authors: Sébastien Mustière, Monika Sester, Frank van Harmelen, and Peter van Oosterom

Published in: Dagstuhl Seminar Proceedings, Volume 9161, Generalization of spatial information (2009)

Abstract
From the early start of handling geo-information in a digital environments, it has been attempted to automate the process of generalization of geographic information. Traditionally for the production of different map scale series, but more and more also in other contexts, such as the desktop/web /mobile use of geo-information, in order to allow to process, handle and understand possibly huge masses of data. Generalization is the process responsible for generating visualizations or geographic databases at coarser levels-of-detail than the original source database, while retaining essential characteristics of the underlying geographic information.
Cite as

Sébastien Mustière, Monika Sester, Frank van Harmelen, and Peter van Oosterom. 09161 Summary – Generalization of spatial information. In Generalization of spatial information. Dagstuhl Seminar Proceedings, Volume 9161, pp. 1-20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2009)

Copy BibTex To Clipboard

@InProceedings{mustiere_et_al:DagSemProc.09161.2,
  author =	{Musti\`{e}re, S\'{e}bastien and Sester, Monika and van Harmelen, Frank and van Oosterom, Peter},
  title =	{{09161 Summary – Generalization of spatial information }},
  booktitle =	{Generalization of spatial information},
  pages =	{1--20},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{9161},
  editor =	{S\'{e}bastien Musti\`{e}re and Monika Sester and Frank van Harmelen and Peter van Oosterom},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.09161.2},
  URN =		{urn:nbn:de:0030-drops-21397},
  doi =		{10.4230/DagSemProc.09161.2},
  annote =	{Keywords: Spatial information, generalization, aggregation, web services, formal semantics, geo-ontology, user context, constraint specification, progressive data transfer, computational geometry, cartography, mobile systems}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact