Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Kai Arulkumaran"'
Publikováno v:
Frontiers in Computational Neuroscience, Vol 18 (2024)
As the apparent intelligence of artificial neural networks (ANNs) advances, they are increasingly likened to the functional networks and information processing capabilities of the human brain. Such comparisons have typically focused on particular mod
Externí odkaz:
https://doaj.org/article/389e4015587d4a57ad287a69178ccd8a
Autor:
Kai Arulkumaran, Marina Di Vincenzo, Rousslan Fernand Julien Dossa, Shogo Akiyama, Dan Ogawa Lillrank, Motoshige Sato, Kenichi Tomeoka, Shuntaro Sasai
Publikováno v:
Frontiers in Robotics and AI, Vol 11 (2024)
Shared autonomy holds promise for assistive robotics, whereby physically-impaired people can direct robots to perform various tasks for them. However, a robot that is capable of many tasks also introduces many choices for the user, such as which obje
Externí odkaz:
https://doaj.org/article/e392db911e7c4b2badc67f2c3e75ef88
Autor:
Tianhong Dai, Kai Arulkumaran, Tamara Gerbert, Samyakh Tukra, Feryal Behbahani, Anil Anthony Bharath
Publikováno v:
Neurocomputing. 493:143-165
Deep reinforcement learning has the potential to train robots to perform complex tasks in the real world without requiring accurate models of the robot or its environment. A practical approach is to train agents in simulation, and then transfer them
Autor:
Kai Arulkumaran, Thu Nguyen-Phuoc
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Publikováno v:
Web of Science
When generating content for video games using procedural content generation (PCG), the goal is to create functional assets of high quality. Prior work has commonly leveraged the feasible-infeasible two-population (FI-2Pop) constrained optimisation al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a7b25a05e89dc57ef75ce4d77b9758c3
http://arxiv.org/abs/2205.05834
http://arxiv.org/abs/2205.05834
In mixed-initiative co-creation tasks, wherein a human and a machine jointly create items, it is important to provide multiple relevant suggestions to the designer. Quality-diversity algorithms are commonly used for this purpose, as they can provide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::637c261da89f3885278004e13bf8dcbe
Publikováno v:
PRICAI 2021: Trends in Artificial Intelligence ISBN: 9783030893699
PRICAI (3)
18th Pacific Rim International Conference on Artificial Intelligence (PRICAI)
PRICAI (3)
18th Pacific Rim International Conference on Artificial Intelligence (PRICAI)
Hindsight experience replay (HER) is a goal relabelling technique typically used with off-policy deep reinforcement learning algorithms to solve goal-oriented tasks; it is well suited to robotic manipulation tasks that deliver only sparse rewards. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::321bc297be2408c75466823c02e70397
http://arxiv.org/abs/2108.07887
http://arxiv.org/abs/2108.07887
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
Publikováno v:
International Workshop on Machine Learning in Medical Imaging
Machine Learning in Medical Imaging ISBN: 9783030598600
MLMI@MICCAI
Machine Learning in Medical Imaging ISBN: 9783030598600
MLMI@MICCAI
Atopic dermatitis (AD), also known as eczema, is one of the most common chronic skin diseases. AD severity is primarily evaluated based on visual inspections by clinicians, but is subjective and has large inter- and intra-observer variability in many
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59f28dded25a4af29754350f277ca082
http://hdl.handle.net/10044/1/82160
http://hdl.handle.net/10044/1/82160