Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Matthew Crosby"'
Autor:
Konstantinos Voudouris, Matthew Crosby, Benjamin Beyret, José Hernández-Orallo, Murray Shanahan, Marta Halina, Lucy G. Cheke
Publikováno v:
Frontiers in Psychology, Vol 13 (2022)
Artificial Intelligence is making rapid and remarkable progress in the development of more sophisticated and powerful systems. However, the acknowledgement of several problems with modern machine learning approaches has prompted a shift in AI benchma
Externí odkaz:
https://doaj.org/article/dcf32291ed06470590ce897acb2d8367
Publikováno v:
PNA: Revista de Investigación en Didáctica de la Matemática, Vol 6, Iss 1, Pp 1-10 (2011)
When arguments are refuted in mathematics classrooms, the ways in which they are refuted can reveal something about the logic of practice evolving in the classroom, as well as about the epistemology that guides the teachers’ teaching. We provide fo
Externí odkaz:
https://doaj.org/article/baf10db9b62a4407acd6a8d6558bf24f
Publikováno v:
Social Robots in Social Institutions ISBN: 9781643683744
Can we build machines with which we can have interesting conversations? Observing the new optimism of AI regarding deep learning and new language models, we set ourselves an ambitious goal: We want to find out how far we can get in creating a digital
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c8a9318ecde16ce0bc6597a49bde05f8
https://doi.org/10.3233/faia220637
https://doi.org/10.3233/faia220637
Publikováno v:
THE 31ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE
We introduce Detect, Understand, Act (DUA), a neuro-symbolic reinforcement learning framework. The Detect component is composed of a traditional computer vision object detector and tracker. The Act component houses a set of options, high-level action
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bfe0b0b99baab1980e610da6869b863c
http://hdl.handle.net/10044/1/101611
http://hdl.handle.net/10044/1/101611
Autor:
Benjamin Beyret, Lucy G. Cheke, Matthew Crosby, Marta Halina, Voudouris K, Murray Shanahan, José Hernández-Orallo
Publikováno v:
Frontiers in Psychology. 13
[EN] Artificial Intelligence is making rapid and remarkable progress in the development of more sophisticated and powerful systems. However, the acknowledgement of several problems with modern machine learning approaches has prompted a shift in AI be
Autor:
Matthew Crosby
Publikováno v:
Minds and Machines. 30:589-615
In ‘Computing Machinery and Intelligence’, Turing, sceptical of the question ‘Can machines think?’, quickly replaces it with an experimentally verifiable test: the imitation game. I suggest that for such a move to be successful the test needs
Autor:
Roger C. Schank, Raúl Rojas, John E. Laird, Kristinn R. Thórisson, François Chollet, Giovanni Granato, Istvan S. N. Berkeley, Alan F. T. Winfield, Roman V. Yampolskiy, Shane Legg, John Fox, Aaron Sloman, Colin W. P. Lewis, Dagmar Monett, Marek Rosa, Peter Lindes, Pei Wang, Joscha Bach, Peter Stone, Richard S. Sutton, Gianluca Baldassarre, Henry Shevlin, Matthew Crosby, William J. Rapaport, Tomas Mikolov
Publikováno v:
Journal of Artificial General Intelligence. 11:1-100
In this paper we introduce Detect, Understand, Act (DUA), a neuro-symbolic reinforcement learning framework. The Detect component is composed of a traditional computer vision object detector and tracker. The Act component houses a set of options, hig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74aa1f26196171db43e7d7003fc32a77
http://hdl.handle.net/10044/1/96353
http://hdl.handle.net/10044/1/96353
Publikováno v:
AI and the Future of Skills, Volume 1 ISBN: 9789264485303
This chapter looks at the basic “common sense” skills needed by artificial intelligence (AI) to perform in the workplace. It begins by focusing on the challenge for AI of navigating in complex and unpredictable environments. It explores the commo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8dcdc6e041495fabec5b98dcab6a709
https://doi.org/10.1787/5fe70a0c-en
https://doi.org/10.1787/5fe70a0c-en
Deep Reinforcement Learning (DRL) is an avenue of research in Artificial Intelligence (AI) that has received increasing attention within the research community in recent years, and is beginning to show potential for real-world application. DRL is one
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c62bd0b2912c6dfb05e21285913bcbb
https://www.repository.cam.ac.uk/handle/1810/318700
https://www.repository.cam.ac.uk/handle/1810/318700