The Experts below are selected from a list of 192 Experts worldwide ranked by ideXlab platform
Carlo Fischione - One of the best experts on this subject based on the ideXlab platform.
-
Wireless for Machine Learning
arXiv: Signal Processing, 2020Co-Authors: Henrik Hellström, José Maitron B, Da Silva, Viktoria Fodor, Carlo FischioneAbstract:As data generation increasingly takes place on devices without a Wired Connection, Machine Learning over wireless networks becomes critical. Many studies have shown that traditional wireless protocols are highly inefficient or unsustainable to support Distributed Machine Learning. This is creating the need for new wireless communication methods. In this survey, we give an exhaustive review of the state of the art wireless methods that are specifically designed to support Machine Learning services. Namely, over-the-air computation and radio resource allocation optimized for Machine Learning. In the over-the-air approach, multiple devices communicate simultaneously over the same time slot and frequency band to exploit the superposition property of wireless channels for gradient averaging over-the-air. In radio resource allocation optimized for Machine Learning, Active Learning metrics allow for data evaluation to greatly optimize the assignment of radio resources. This paper gives a comprehensive introduction to these methods, reviews the most important works, and highlights crucial open problems.
Henrik Hellström - One of the best experts on this subject based on the ideXlab platform.
-
Wireless for Machine Learning
arXiv: Signal Processing, 2020Co-Authors: Henrik Hellström, José Maitron B, Da Silva, Viktoria Fodor, Carlo FischioneAbstract:As data generation increasingly takes place on devices without a Wired Connection, Machine Learning over wireless networks becomes critical. Many studies have shown that traditional wireless protocols are highly inefficient or unsustainable to support Distributed Machine Learning. This is creating the need for new wireless communication methods. In this survey, we give an exhaustive review of the state of the art wireless methods that are specifically designed to support Machine Learning services. Namely, over-the-air computation and radio resource allocation optimized for Machine Learning. In the over-the-air approach, multiple devices communicate simultaneously over the same time slot and frequency band to exploit the superposition property of wireless channels for gradient averaging over-the-air. In radio resource allocation optimized for Machine Learning, Active Learning metrics allow for data evaluation to greatly optimize the assignment of radio resources. This paper gives a comprehensive introduction to these methods, reviews the most important works, and highlights crucial open problems.
Sylvain Ballandras - One of the best experts on this subject based on the ideXlab platform.
-
High temperature packaging for surface acoustic wavetransducers acting as passive wireless sensors
Sensors and Actuators A: Physical, 2015Co-Authors: Bruno Francois, Jean Friedt, Gilles Martin, Sylvain BallandrasAbstract:Numerous developments have been dedicated these passed years to demonstrate the use of surface acoustic wave (SAW) devices as passive sensors probed through a wireless radio-frequency link. Giving access to physical parameter variations without embedded power supply, recent works have shown that SAW sensors can be used under harsh environments such as temperatures in excess of 300 °C and much more. The purpose of this paper is to present a new packaging process for SAW sensors operating under temperature environments up to 600 °C. The robustness of this packaging process is first validated at the above-mentioned temperature using a classical temperature probe via Wired Connection. The reliability of this process applied to differential SAW sensors then is demonstrated by wireless interrogation of a quartz-based SAW differential sensor from room temperature to 480 °C. The sensor operation has been validated for several tens of hours without major failure nor significant deviation, although the measurement distance dynamic range is observed to be dramatically reduced with operating on such a wide temperature range.
José Maitron B - One of the best experts on this subject based on the ideXlab platform.
-
Wireless for Machine Learning
arXiv: Signal Processing, 2020Co-Authors: Henrik Hellström, José Maitron B, Da Silva, Viktoria Fodor, Carlo FischioneAbstract:As data generation increasingly takes place on devices without a Wired Connection, Machine Learning over wireless networks becomes critical. Many studies have shown that traditional wireless protocols are highly inefficient or unsustainable to support Distributed Machine Learning. This is creating the need for new wireless communication methods. In this survey, we give an exhaustive review of the state of the art wireless methods that are specifically designed to support Machine Learning services. Namely, over-the-air computation and radio resource allocation optimized for Machine Learning. In the over-the-air approach, multiple devices communicate simultaneously over the same time slot and frequency band to exploit the superposition property of wireless channels for gradient averaging over-the-air. In radio resource allocation optimized for Machine Learning, Active Learning metrics allow for data evaluation to greatly optimize the assignment of radio resources. This paper gives a comprehensive introduction to these methods, reviews the most important works, and highlights crucial open problems.
Da Silva - One of the best experts on this subject based on the ideXlab platform.
-
Wireless for Machine Learning
arXiv: Signal Processing, 2020Co-Authors: Henrik Hellström, José Maitron B, Da Silva, Viktoria Fodor, Carlo FischioneAbstract:As data generation increasingly takes place on devices without a Wired Connection, Machine Learning over wireless networks becomes critical. Many studies have shown that traditional wireless protocols are highly inefficient or unsustainable to support Distributed Machine Learning. This is creating the need for new wireless communication methods. In this survey, we give an exhaustive review of the state of the art wireless methods that are specifically designed to support Machine Learning services. Namely, over-the-air computation and radio resource allocation optimized for Machine Learning. In the over-the-air approach, multiple devices communicate simultaneously over the same time slot and frequency band to exploit the superposition property of wireless channels for gradient averaging over-the-air. In radio resource allocation optimized for Machine Learning, Active Learning metrics allow for data evaluation to greatly optimize the assignment of radio resources. This paper gives a comprehensive introduction to these methods, reviews the most important works, and highlights crucial open problems.
