imec is the world-leading research and innovation hub in nanoelectronics and digital technologies. The combination of our widely acclaimed leadership in microchip technology and profound software and ICT expertise is what makes us unique. By leveraging our world-class infrastructure and local and global ecosystem of partners across a multitude of industries, we create groundbreaking innovation in application domains such as healthcare, smart cities and mobility, logistics and manufacturing, and energy.
University of Antwerp – imec IDLab Research group
The IDLab research group of imec and the University of Antwerp performs fundamental and applied research on internet technologies and data science. The overall IDLab research areas are machine learning and data mining; semantic intelligence; distributed intelligence for IoT; cloud and big data infrastructures; multimedia coding and delivery; wireless and fixed networking; electromagnetics, RF and high-speed circuits and systems. Within Antwerp, IDLab specifically focuses on wireless networking and distributed intelligence. IDLab has a unique research infrastructure used in numerous national and international collaborations.
IDLab collaborates with many universities and research centres worldwide and jointly develops advanced technologies with industry (R&D centers from international companies, Flanders’ top innovating large companies and SME’s, as well as numerous ambitious startups).
For further development of the IDLab machine learning research cluster, we are looking for a PhD researcher in the domain of machine learning for wearables.
The research project
Deep Learning has provided tremendous breakthroughs over the last few years in domains such as natural language process, computer vision and video game strategies. Part of this success is due to the availability of huge amounts of (labeled) data and ample computing power. As a result, many of the deep learning successes require an architecture where a large neural network model can be trained and inferred in the cloud.
On the contrary, many real-life applications require the complete opposite model. For both technical and non-technical reasons, learning and/or inference should happen at the edge of the network, where resources are much scarcer. This scarcity can either be a lack of (labeled) data, computing power, energy, networking resources or a combination of the above. In this research project, you will be developing new deep learning algorithms that are specifically optimized for such resource poor environments. Examples of these include label efficient learning algorithms, learning in sparse reward settings, effectively employing simulation, learning on spatio temporal data, etc.
For more information, please contact