KU Leuven K

Waves: Core Research and Engineering (WaveCore), Leuven (Arenberg) (BB-2B194)

Trouvé dans: Xpatjobs BE

The research group ESAT-WAVECORE of the Department of Electrical Engineering (ESAT) focuses on Wireless Communication. Within WAVECORE, the Networked Systems group covers research on several fields of wireless networking: Massive MIMO, UAV communications, mmWave, AI and Machine Learning, and Internet of Things. Networked Systems is looking for a suitable candidate to pursue a PhD in the topic of energetically self-sustainable beyond-5G mobile edge networks. In this PhD project, the aim is to combine expertise from ESAT-WAVECORE on 5G and AI, with various partners to tackle the huge energy consumption problem of computing and AI applications.Required:At the time of recruitment, the applicant must not have lived in Belgium for more than 12 months in the previous 36 months (3 years).
Required:No more than 4 years spent in research/work activities after the achievement of the MS degree.
Preferred:A Masters degree in Telecommunications, Computer Science, DataScience or equivalent.
Preferred:Very good communication skills in oral and written English.
Preferred:Background in wireless communication, performance modelling oroptimization
Preferred:Open-mindedness, strong integration skills and team spirit.
Desired:good command of the Python programming language.
Desired:previous training MS-level training on machine learning techniques.
Extreme edge computing assumes that significant processing can run on the sensors. Ideally, extreme edge processing can exploit the energy harvested from the environment, which means that energy supply is irregular. Intermittent computing divides complex tasks in small steps that can be executed when there is just enough energy available. Intermediate results are then saved efficiently so that the sensors can go into a deep sleep state. When new energy is available, the sensor can wake-up and resume the processing. Interesting platforms are being proposed in the state of the art for addingdeep learning acceleration on the sensors, such as Googles coral platform. Objectivesare: (1) To study how much of the anomaly detection pipeline can run locally, and how many/much features/data should be communicated to the cloud for further processing there. (2) To co-design the local algorithms for various deep learning architectures, to make sure the algorithms match the chosen architectures optimally. A logical step is here for instance the use of quantized models. Beyond that, there also exist interesting approaches to achieve structured sparsity, and hence simpler models. (3) To divide the models into small parts that can be executed intermittently, while trading off memory access cost likelihood of losing intermediate results.
Once hired, the candidate will:
  • be working at KU Leuven, performing full-time research under the supervision of Prof.Sofie Pollin.
  • will be enrolled in the PhD program at KU Leuven, under the supervision of Prof. SofiePollin.
  • will additionally pursue two secondments at OULU and WSE, for a respective durationof 5 and 5 months.

calendar_todayil y a 2 jours


location_on Leuven , Flanders, Belgique

work KU Leuven

J'autorise expressément le Conditions générales

Emplois similaires