Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Kai Olav Ellefsen"'
Publikováno v:
Frontiers in Robotics and AI, Vol 8 (2021)
In modular robotics modules can be reconfigured to change the morphology of the robot, making it able to adapt to specific tasks. However, optimizing both the body and control of such robots is a difficult challenge due to the intricate relationship
Externí odkaz:
https://doaj.org/article/6201812a3a604baba9877e46021c097e
Publikováno v:
PLoS Computational Biology, Vol 11, Iss 4, p e1004128 (2015)
A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new
Externí odkaz:
https://doaj.org/article/a521a3ada02e4d25a41b2c6fbced491d
Publikováno v:
IEEE Transactions on Cognitive and Developmental Systems. 14:1302-1305
Publikováno v:
2022 18th International Conference on Network and Service Management (CNSM).
Publikováno v:
2022 IEEE 47th Conference on Local Computer Networks (LCN).
Autor:
Orjan Strand, Didrik Spanne Reilstad, Zhenying Wu, Bruno Castro Da Silva, Jim Torresen, Kai Olav Ellefsen
Publikováno v:
2022 IEEE International Conference on Development and Learning (ICDL).
Publikováno v:
2021 17th International Conference on Network and Service Management (CNSM).
Neural networks have been widely used in agent learning architectures; however, learnings for one task might nullify learnings for another. Behavioural plasticity enables humans and animals alike to respond to environmental changes without degrading
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76d2792c2da15d5b5db31ab165443c20
http://hdl.handle.net/10852/90350
http://hdl.handle.net/10852/90350
Publikováno v:
Applications of Evolutionary Computation ISBN: 9783030726980
EvoApplications
EvoApplications
Designing robots by hand can be costly and time consuming, especially if the robots have to be created with novel materials, or be robust to internal or external changes. In order to create robots automatically, without the need for human interventio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a9734dd7c268d381e7eeae2a6390156
https://doi.org/10.1007/978-3-030-72699-7_3
https://doi.org/10.1007/978-3-030-72699-7_3
Autor:
Kai Olav Ellefsen, Patrick Ribu Gorton
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030717100
Predicting the future using deep learning models is a research field of increasing interest. However, there is a lack of established evaluation methods for assessing their predictive abilities. Images and videos are targeted towards human observers,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a36c18c7942b5726bf354ce158c397a
https://doi.org/10.1007/978-3-030-71711-7_12
https://doi.org/10.1007/978-3-030-71711-7_12