PhD researcher on Next Generation Neural Networks

Job description

IMEC

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 next generation neural networks. 


The research project

State-of-the-art artificial neural networks have achieved remarkable successes in terms of accuracy in a variety of AI-related tasks. Part of this success is due to the availability of huge amounts of (labeled) data and ample computing power for off-line training. However, in many real-life applications there is a need to be able to train or online adapt these networks with only limited amount of labeled data, and robust networks that can be executed on small and low power devices.


In this research project, you will investigate new brain-inspired ideas that go beyond the current 2nd generation networks (e.g. spiking neurons, temporal coding, learning with hyper-vectors, …) with the aim of designing solutions with high accuracy, but that can also learn new concepts from only a limited number of examples, are robust to noise, and allow for low power implementations.


The job

  • You are conducting research in the IDLab distributed intelligence team, enhancing, applying or extending brain-inspired learning algorithms and creating new ones.
  • You will implement novel neural network architectures and algorithms, and conduct experiments to compare the new algorithms with existing state-of-the-art methods
  • You will write detailed evaluation reports on the developed algorithms and executed experiments, publishing them in major conferences and journals.
  • You will develop demonstrators in the framework of European and national research projects (in collaboration with industry).

For more information, please contact  Hanne.Everts@uantwerpen.be

Requirements

  • You have or will soon obtain a Master of Science degree, preferably in Computer Science, Engineering, Mathematics, Biology, Physics, Electrical Engineering, or equivalent.
  • You have experience with programming languages and software development
  • You have a profound interest in artificial intelligence and machine learning. Knowledge on artificial and/or spiking neural networks is an additional asset.
  • You are a team player and have strong communication skills.
  • Your English is fluent, both speaking and writing.