Post-doctoral researcher in hardware-efficient inference and training of neural networks

Gent - PostDoc
|
Meer dan twee weken geleden

Your focus will be on future application domains such as audio processing or cognitive robotics. 

Solliciteer

imec-IDLAB-UGent

IDLab is a research group of Ghent University, as well as a core research group of imec.  IDLab performs fundamental and applied research on data science and internet technology, and counts over 300 researchers.  Our major research areas are machine learning and data mining; semantic intelligence; multimedia processing; distributed intelligence for IoT; cloud and big data infrastructures; wireless and fixed networking; electromagnetics, RF and high-speed circuits and systems. 
IDLab is also part of imec, 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 ground-breaking innovation in application domains such as healthcare, smart cities and mobility, logistics and manufacturing, and energy.

What will you do

Various forms of neural networks (CNN, LSTM, spiking neural networks) have realized important breakthroughs in a myriad of application domains. The dominant model today is to train neural networks in the cloud on a large set of labelled data in a hardware-agnostic way. Afterwards, inference either always occurs in the cloud, or in some specific cases, the neural network is compressed, pruned, and quantized for mapping on lower footprint devices. This current model does not allow for efficient online learning on the device itself. There are however several dynamic environments where additional online learning and on-device learning capabilities are required to discover new categories and tasks to adapt a task to the specific environment.

We are looking for an excellent post-doc to conduct research in this domain. The exact topic depends on the candidate interests and qualification, and may be situated a.o. in:

  • quantized training techniques for artificial neural networks
  • modular artificial neural networks
  • uncertainty quantification of neural networks, e.g. using Bayesian Neural networks
  • neuromorphic sensors and platforms
  • algorithms based on spiking neural network: online learning

The research is fundamental in nature but with a clear focus on future application domains such as audio processing or cognitive robotics. 
Part of the responsibilities of the post-doc are to help the faculty staff with defining research roadmaps, day-to-day supervision of PhD students and proposal writing.

What we do for you

We offer a full time contract, with a temporary assignment of 12 months that can be extended upon positive evalution. The research is fundamental and innovative, but with clear practical applications. You will join a young and enthusiastic team of researchers, post-docs and professors. The post-doc position is immediately available.

Who you are

  • You have (or will obtain in the near future) a PhD degree in in Computer Science, Electronics, or (Mathematical) Informatics.
  • You have published in high-ranking conference and/or journals in the field
  • Experience with managing and supervising team members; or with participating in national/international research projects is a plus.
  • You have proven experience in one or more of the research domains listed above
  • You have excellent analytical skills.
  • You speak and write English fluently (C1 CEFR level).
  • You have good communication skills.
  • You have an open mind and a multi-disciplinary attitude.
  • You are eligible for a Flemish PhD scholarship (i.e., you have not enjoyed such a scholarship before).

Interested?

Apply with motivation letter, scientific resume, two reference contacts, your top publication(s) and an abstract of your PhD dissertation. This information, as well as possible questions, must be sent to Prof. Pieter Simoens at pieter.simoens@ugent.be. After the first screening, suitable candidates will be invited for an interview (also possible via Skype) and may get a small assignment. Applications will be screened as soon as they are received. The position is open until the vacancy is filled.
 

Solliciteer

Share this on

truetrue

Deze website maakt gebruik van cookies met als enige doel het analyseren van surfgedrag, zonder enige commerciƫle insteek. Lees er hier meer over. Lees ook ons privacy statement. Sommige inhoud (video's, iframes, formulieren,...) op deze website zal pas zichtbaar zijn na het accepteren van de cookies.

Accepteer cookies