Zobrazeno 1 - 10
of 87
pro vyhledávání: '"Thórisson, Kristinn R."'
Autor:
Latapie, Hugo, Yu, Shan, Hammer, Patrick, Thorisson, Kristinn R., Petrosyan, Vahagn, Kynoch, Brandon, Khare, Alind, Behnam, Payman, Tumanov, Alexey, Saxena, Aksheit, Aralikatti, Anish, Chen, Hanning, Imani, Mohsen, Archbold, Mike, Li, Tangrui, Wang, Pei, Hart, Justin
Traditional computer vision models often necessitate extensive data acquisition, annotation, and validation. These models frequently struggle in real-world applications, resulting in high false positive and negative rates, and exhibit poor adaptabili
Externí odkaz:
http://arxiv.org/abs/2307.10577
A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience. This involves managing an agent's goals as well as cont
Externí odkaz:
http://arxiv.org/abs/2112.01603
Autor:
Latapie, Hugo, Kilic, Ozkan, Liu, Gaowen, Yan, Yan, Kompella, Ramana, Wang, Pei, Thorisson, Kristinn R., Lawrence, Adam, Sun, Yuhong, Srinivasa, Jayanth
This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation. While interest in hybrid machine learning / symbolic AI systems leveraging, for example, reasoning and knowledge grap
Externí odkaz:
http://arxiv.org/abs/2102.06112
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Thórisson, Kristinn R., Bieger, Jordi, Thorarensen, Thröstur, Sigurðardóttir, Jóna S., Steunebrink, Bas R.
The concept of "task" is at the core of artificial intelligence (AI): Tasks are used for training and evaluating AI systems, which are built in order to perform and automatize tasks we deem useful. In other fields of engineering theoretical foundatio
Externí odkaz:
http://arxiv.org/abs/1604.04660
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Biologically Inspired Cognitive Architectures July 2013 5:52-63
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Aliman, Nadisha Marie, Elands, Pieter, Hürst, Wolfgang, Kester, Leon, Thórisson, Kristinn R., Werkhoven, Peter, Yampolskiy, Roman, Ziesche, Soenke, Goertzel, Ben, Potapov, Alexey, Panov, Aleksandr I.
The complex socio-technological debate underlying safety-critical and ethically relevant issues pertaining to AI development and deployment extends across heterogeneous research subfields and involves in part conflicting positions. In this context, i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______101::e646785cd839af878c014030dd785179
https://dspace.library.uu.nl/handle/1874/414626
https://dspace.library.uu.nl/handle/1874/414626
Autor:
Thórisson, Kristinn R., Bieger, J.E., Li, X., Wang, Pei, Hammer, Patrick, Agrawal, Pulin, Goertzel, Ben, Iklé, Matthew
Publikováno v:
Artificial General Intelligence ISBN: 9783030270049
Artificial General Intelligence-12th International Conference, AGI 2019, Proceedings
Artificial General Intelligence-12th International Conference, AGI 2019, Proceedings
An important feature of human learning is the ability to continuously accept new information and unify it with existing knowledge, a process that proceeds largely automatically and without catastrophic side-effects. A generally intelligent machine (A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e86e1a05dbada758dec3c8c254a05f0
https://doi.org/10.1007/978-3-030-27005-6_20
https://doi.org/10.1007/978-3-030-27005-6_20