Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Marios Daoutis"'
Publikováno v:
2022 IEEE Wireless Communications and Networking Conference (WCNC).
Spiking neural networks (SNN) are expected to enable several use-cases in future communication networks (beyond 5G and 6G), as edge AI and battery-constrained systems can leverage the fast computation and high-power efficiency offered by SNNs. In thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f60a6838987dbd99c0c796e8f94dc7d
https://doi.org/10.1109/wcnc51071.2022.9771543
https://doi.org/10.1109/wcnc51071.2022.9771543
Publikováno v:
2022 IEEE Wireless Communications and Networking Conference (WCNC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ec3bbc26b08bd91ed112e2a4be0ef0b
https://doi.org/10.1109/wcnc51071.2022.9771766
https://doi.org/10.1109/wcnc51071.2022.9771766
Publikováno v:
The Knowledge Engineering Review. 37
Reinforcement Learning (RL) methods often rely on gradient estimates to learn an optimal policy for control problems. These expensive computations result in long training times, a poor rate of convergence, and sample inefficiency when applied to real
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f910100c39e9a6e29bb5c49d8c17c7bb
https://doi.org/10.1017/s0269888922000042
https://doi.org/10.1017/s0269888922000042
Autor:
Marios Daoutis, Aneta Vulgarakis Feljan, Marin Orlic, Michael Cashmore, Daniele Magazzeni, Dorian Buksz, Swarup Kumar Mohalik, Ramamurthy Badrinath, Anusha Mujumdar
Publikováno v:
IROS
Realization of industry-scale, goal-driven, autonomous systems with AI planning technology faces several challenges: flexibly specifying planning goal states in varying situations, synthesizing plans in large state spaces, re-planning in dynamic situ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::55a474c966f55afb7f90e6e8a4674949
https://strathprints.strath.ac.uk/73423/1/Buksz_etal_IROS_2020_Intent_driven_strategic_tactical_planning_for_autonomous_site_inspection.pdf
https://strathprints.strath.ac.uk/73423/1/Buksz_etal_IROS_2020_Intent_driven_strategic_tactical_planning_for_autonomous_site_inspection.pdf
Autor:
Marios Daoutis
Publikováno v:
KI - Künstliche Intelligenz. 27:179-182
Perceptual anchoring is the process of creating and maintaining a connection between the sensor data corresponding to a physical object and its symbolic description. It is a subset of the symbol grounding problem, introduced by Harnad (Phys. D, Nonli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::19278afadd29e83d2f826d68e6479919
https://doi.org/10.1007/s13218-013-0249-0
https://doi.org/10.1007/s13218-013-0249-0
Publikováno v:
Intelligent Service Robotics. 5:213-228
We present a model for anchoring categorical conceptual information which originates from physical perception and the web. The model is an extension of the anchoring framework which is used to create and maintain over time semantically grounded senso
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::446369f6287a76742f73796ad0535697
https://doi.org/10.1007/s11370-012-0117-z
https://doi.org/10.1007/s11370-012-0117-z
Publikováno v:
Journal of Ambient Intelligence and Smart Environments. 1:311-321
Ambient environments which integrate a number of sensing devices and actuators intended for use by human users need to be able to express knowledge about objects, their functions and their properties to assist in the performance of everyday tasks. Fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8adbb5a93fc05d0ca053495016e83390
https://doi.org/10.3233/ais-2009-0040
https://doi.org/10.3233/ais-2009-0040
Autor:
Marios Daoutis, Mathias Broxvall
GPU’s have recently emerged as a significantly more powerful computing plat-form, capable of several orders of magnitude faster computations compared toCPU based approaches. However, they require significant changes in the algorithmic design compar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::538ed13dd68d25d2654bb8a55d5dc5c4
https://doi.org/10.1142/9789814460941_0014
https://doi.org/10.1142/9789814460941_0014
In settings where heterogenous robotic systems interact with humans, information from the environment must be systematically captured, organized and maintained in time. In this work, we propose a model for connecting perceptual information to semanti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f55f1d155bd992ad3160d0ff15d3d53
http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-24226
http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-24226
Publikováno v:
Publikationer från Örebro universitet.
In this work we introduce symbolic knowledge representation and reasoning capabilities to enrich perceptual anchoring. The idea that encompasses perceptual anchoring is the creation and maintenance of a connection between the symbolic and perceptual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::221fcd1bb835bd06da3ae34c5f45331c
http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-5175
http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-5175