Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Steven Bohez"'
Autor:
Sam Leroux, Bert Vankeirsbilck, Bart Dhoedt, Tim Verbelen, Steven Bohez, Elias De Coninck, Pieter Simoens
Publikováno v:
JOURNAL OF SYSTEMS AND SOFTWARE
Deep learning has shown tremendous results on various machine learning tasks, but the nature of the problems being tackled and the size of state-of-the-art deep neural networks often require training and deploying models on distributed infrastructure
Autor:
Elias De Coninck, Sam Leroux, Steven Bohez, Pieter Simoens, Bart Dhoedt, Tim Verbelen, Bert Vankeirsbilck
Publikováno v:
KNOWLEDGE AND INFORMATION SYSTEMS
Most of the research on deep neural networks so far has been focused on obtaining higher accuracy levels by building increasingly large and deep architectures. Training and evaluating these models is only feasible when large amounts of resources such
Autor:
Sam Leroux, Pieter Van Molle, Steven Bohez, Pieter Simoens, Bart Dhoedt, Bert Vankeirsbilck, Elias De Coninck, Tim Verbelen
Publikováno v:
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
Internet of Things (IoT) infrastructures are more and more relying on multimedia sensors to provide information about the environment. Deep neural networks (DNNs) could extract knowledge from this audiovisual data but they typically require large amo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::829f3e133d9bde91728a2e15da36ec8f
https://biblio.ugent.be/publication/8619122
https://biblio.ugent.be/publication/8619122
Autor:
Elias De Coninck, Steven Bohez, Pieter Simoens, Tim Verbelen, Bert Vankeirsbilck, Bart Dhoedt
Publikováno v:
Journal of Systems and Software. 118:101-114
Provisioning cloud resources based on monitoring information and simulations.CloudSim simulations based on real service workloads to improve knowledge model.Scheduling deadline constrained service workloads on multiple cloud infrastructures. Cloud sy
Publikováno v:
NOMS
Internet applications rely on strong encryption techniques to protect the content of all communications between client and server. These encryption algorithms ensure that third parties are unable to obtain the plain text data but also make it hard fo
Autor:
Vincent Vanhoucke, Danijar Hafner, Steven Bohez, Jie Tan, Tingnan Zhang, Atil Iscen, Yunfei Bai, Erwin Coumans
Publikováno v:
Robotics: Science and Systems
Designing agile locomotion for quadruped robots often requires extensive expertise and tedious manual tuning. In this paper, we present a system to automate this process by leveraging deep reinforcement learning techniques. Our system can learn quadr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cdba5c4a915482b7384fe60d0baff2d9
Autor:
Matthias De Geyter, Steven Bohez, Sam Decrock, Pieter Simoens, Glenn Van Wallendael, Niels Van Kets, Steven Latre, Jeroen Famaey, Glenn Daneels, Peter Lambert, Bart Dhoedt, Lander Van Herzeele
Publikováno v:
MULTIMEDIA TOOLS AND APPLICATIONS
Multimedia tools and applications
Multimedia tools and applications
Recording videos with smartphones at large-scale events such as concerts and festivals is very common nowadays. The se videos register the atmosphere of the event as it is experienced by the crowd and offer a perspective that is hard to capture by th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::86dc6eb47d6cf9819050094565e30b1e
https://biblio.ugent.be/publication/8547200
https://biblio.ugent.be/publication/8547200
Publikováno v:
SIMULATION MODELLING PRACTICE AND THEORY
The deployment of highly interactive, media-rich applications on mobile devices is hindered by the inherent limitations on compute power, memory and battery capacity of these hand-held platforms. The cloudlet concept, opportunistically offloading com
Autor:
Elias De Coninck, Tim Verbelen, Bert Vankeirsbilck, Steven Bohez, Pieter Simoens, Bart Dhoedt
Publikováno v:
Ghent University Academic Bibliography
IROS
IROS
Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In addition to s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7610bcb850e92a3c2141685895c6fd6d
http://arxiv.org/abs/1703.04550
http://arxiv.org/abs/1703.04550
Autor:
Bart Dhoedt, Sam Leroux, Tim Verbelen, Elias De Coninck, Bert Vankeirsbilck, Steven Bohez, Pieter Simoens
Publikováno v:
CloudNet
2016 5TH IEEE INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (IEEE CLOUDNET)
2016 5TH IEEE INTERNATIONAL CONFERENCE ON CLOUD NETWORKING (IEEE CLOUDNET)
Cyber-physical systems in the factory of the future will consist of cloud-hosted software governing an agile production process executed by autonomous mobile robots and controlled by analyzing the data from a vast number of sensors. CPSs thus operate