Zobrazeno 1 - 10
of 278
pro vyhledávání: '"Frank Van Harmelen"'
Autor:
Hannes Werthner, Frank van Harmelen
This book is open access under a CC BY-NC 4.0 license.This volume discusses the prospects and evolution of informatics (or computer science), which has become the operating system of our world, and is today seen as the science of the information soci
Publikováno v:
Data Science. 5:167-193
Open access to datasets is increasingly driving modern science. Consequently, discovering such datasets is becoming an important functionality for scientists in many different fields. We investigate methods for dataset recommendation: the task of rec
Publikováno v:
den Hengst, F, François-Lavet, V, Hoogendoorn, M & van Harmelen, F 2022, ' Planning for potential: efficient safe reinforcement learning ', Machine Learning, vol. 111, no. 6, pp. 2255-2274 . https://doi.org/10.1007/s10994-022-06143-6
Machine Learning, 111(6), 2255-2274. Springer Netherlands
Machine Learning, 111(6), 2255-2274. Springer Netherlands
Deep reinforcement learning (DRL) has shown remarkable success in artificial domains and in some real-world applications. However, substantial challenges remain such as learning efficiently under safety constraints. Adherence to safety constraints is
Publikováno v:
Machine Learning.
Recent work has shown logical background knowledge can be used in learning systems to compensate for a lack of labeled training data. Many methods work by creating a loss function that encodes this knowledge. However, often the logic is discarded aft
Autor:
Anna Breit, Laura Waltersdorfer, Fajar J. Ekaputra, Marta Sabou, Andreas Ekelhart, Andreea Iana, Heiko Paulheim, Jan Portisch, Artem Revenko, Annette ten Teije, Frank van Harmelen
Publikováno v:
ACM Computing Surveys.
In line with the general trend in artificial intelligence research to create intelligent systems that combine learning and symbolic components, a new sub-area has emerged that focuses on combining machine learning (ML) components with techniques deve
Publikováno v:
The Semantic Web ISBN: 9783031334542
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af87365da1d78bb6b55b4e1bceaf1606
https://doi.org/10.1007/978-3-031-33455-9_4
https://doi.org/10.1007/978-3-031-33455-9_4
Publikováno v:
Semantic Web. 12:21-40
Matching entities between datasets is a crucial step for combining multiple datasets on the semantic web. A rich literature exists on different approaches to this entity resolution problem. However, much less work has been done on how to assess the q
Publikováno v:
Data Intelligence, 2(3), 323-352
Data Intelligence, Vol 2, Iss 3, Pp 323-352 (2020)
Raad, J, Beek, W, van Harmelen, F, Wielemaker, J, Pernelle, N & Saïs, F 2020, ' Constructing and cleaning identity graphs in the lod cloud ', Data Intelligence, vol. 2, no. 3, pp. 323-352 . https://doi.org/10.1162/dint_a_00057
Data Intelligence, 2(3), 323-352. China National Publications Import and Export (Group) Corporation
International Journal of Big Data Intelligence
International Journal of Big Data Intelligence, Inderscience Publishers, 2020, 2 (3), pp.323-352. ⟨10.1162/dint_a_00057⟩
Data Intelligence, Vol 2, Iss 3, Pp 323-352 (2020)
Raad, J, Beek, W, van Harmelen, F, Wielemaker, J, Pernelle, N & Saïs, F 2020, ' Constructing and cleaning identity graphs in the lod cloud ', Data Intelligence, vol. 2, no. 3, pp. 323-352 . https://doi.org/10.1162/dint_a_00057
Data Intelligence, 2(3), 323-352. China National Publications Import and Export (Group) Corporation
International Journal of Big Data Intelligence
International Journal of Big Data Intelligence, Inderscience Publishers, 2020, 2 (3), pp.323-352. ⟨10.1162/dint_a_00057⟩
International audience; In the absence of a central naming authority on the Semantic Web, it is common for different data sets to refer to the same thing by different names. Whenever multiple names are used to denote the same thing, owl:sameAs statem
Publikováno v:
SSRN Electronic Journal.
Publikováno v:
van Krieken, E, Acar, E & van Harmelen, F 2022, ' Analyzing Differentiable Fuzzy Logic Operators ', Artificial Intelligence, vol. 302, 103602, pp. 1-46 . https://doi.org/10.1016/j.artint.2021.103602
Artificial Intelligence
Vrije Universiteit Amsterdam
Artificial Intelligence, 302:103602, 1-46. Elsevier
Artificial Intelligence
Vrije Universiteit Amsterdam
Artificial Intelligence, 302:103602, 1-46. Elsevier
The AI community is increasingly putting its attention towards combining symbolic and neural approaches, as it is often argued that the strengths and weaknesses of these approaches are complementary. One recent trend in the literature are weakly supe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c0d6db48febc84f534077013443d5a5
https://hdl.handle.net/1871.1/f15f988d-2211-467b-95c8-dd7b5779f947
https://hdl.handle.net/1871.1/f15f988d-2211-467b-95c8-dd7b5779f947