Vacancy: PhD student on adaptive deep learning techniques for high-dimensional surveillance data in a smart city

(05-04-2019) We are looking for an excellent PhD student to work on adaptive deep learning techniques. The research will be conducted in the context of a research project on smart city data, in collaboration with industry.

The research group: 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.

The job

Data is a cornerstone of any smart city. Video and audio, captured by surveillance cameras and microphones, can provide a lot of contextual information. To extract information from high-dimensional raw data, deep learning techniques are the current state-of-art. Yet, today’s deployment model of pretraining in the cloud on a labelled dataset is not suited for dynamic contexts such as smart cities. Every location has its very own specific set of objects in view, sounds that can occur (e.g. a train station compared to a city center), spatial acoustics, etc. Moreover these dynamic contexts will evolve over time, e.g. diurnal patterns, weather conditions change of traffic direction, etc. This requires neural network models that are flexible enough to continuously adapt themselves in an unsupervised way. Moreover, it is an open question whether these models should run on the sensing device, or whether they can be partially offloaded to the cloud.

We are looking for an excellent PhD student to work on adaptive deep learning techniques. Fundamental research questions that will be addressed in this thesis are:

  1. How to design neural models with a flexible inference path, e.g. using a modular architecture or with gating techniques, as opposed to today’s approach where the computational path is identical for each sample (each sample requires the same number of operations)?
  2. How to design generative models with an adaptive modelling capacity, powerful enough to model smart city data in a tractable latent space?
  3. How to ensure privacy requirements when processing audio and video? Should the entire neural network run on the device, or can a neural network on the device generate feature descriptors that are powerful enough to allow for classification yet obfuscate sensitive information?

The research will be conducted in the context of a research project on smart city data, in collaboration with industry.


  • You have a degree in Master of Science/Engineering, preferably in Computer Science, Electronics, or (Mathematical) Informatics. Note: to be admissible to the PhD-program, your degree must be equivalent to 5 years of engineering studies (bachelor + master) in the European Union, and you must have a solid academic track record (graduation cum laude or grades in the top 15% percentile). Please do not hesitate to contact us regarding these administrative matters.
  • You have knowledge of and experience with machine learning.
  • You have a strong interest in one or more of the following domains: deep learning with artificial neural networks, online learning. Proven experience in one of these domains, e.g. via your master thesis topic or projects, is a plus.
  • You are interested in and motivated by the research topic and the use case, as well as in obtaining a PhD degree.
  • 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).

Our offer

We offer a fully funded PhD scholarship for a maximal period of 4 years (upon positive progress evaluation). The PhD 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 PhD position is immediately available.


Apply with motivation letter, scientific resume, abstract of your master thesis, diplomas and detailed academic results (courses and grades), relevant publications, and at least one reference contact. This information, as well as possible questions, must be sent to Prof. Pieter Simoens at
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.

Read more articles about: