PhD Position in Uncertainty Modelling for Artificial Intelligence-Based Algorithms Within Distributed Autonomous Systems
Catholic University of Leuven
Belgium

The M-Group or Mechatronics Groups is multi-departemental research group involving the Departments of Mechanical Engineering, Electrical Engineering, and Computer Science and is located at the brand new campus at Bruges, one of the KU Leuven Campusses within the Flanders of Belgium. The research group M-Group (Mechatronics Group) of KU Leuven focuses on the design, development and validation of dependable interconnected mechatronic systems, with dependability being defined as the ability of a system to provide its services in a way that can defensibly be trusted with modelling advanced uncertainty capability. The M-group has several labs equipped with state-of-the-art infrastructure to build, test and investigate mechatronic systems and self-organising production systems. The research group is a multidisciplinary team of professors and researcher skilled in hardware design, software engineering and mechanical eningeering. The research is focussed toward reliable and sustainable performance of systems considering mechanical aspects, electrical energy, automation, electronics, signal processing and ICT. The research group consists of 4 professors and 20 post-docs, research assistants or PhD student. Here, the research team can make use of state-of-the-art research equipment and infrastructure such as the Ultimate Factory Lab or the Ultimate Machine Lab. Furthermore, the available infrastructure allows the PhD students and research assistants to design and develop robust and dependable design techniques for hardware or software. The research group has been succesfull in acquiring prestigious funding such as H2020, Marie Slodowska-Curie Actions and national funding (FWO, imec.ICON,...). For years, the research group maintains a close collaboration with other research groups from KU Leuven within the departments of Computer Science (imec.Distrinet), Mechanics (LMSD, RAM,TME) and Electrical Engineering (Wave:Core).

Project

Although artificial intelligence (AI) has improved remarkably over the last years, its inability to deal with fundamental uncertainty severely limits its application. This project re-imagines AI with a proper treatment of the uncertainty stemming from our forcibly partial knowledge of the world. As currently practiced, AI cannot confidently make predictions robust enough to stand the test of data generated by processes different (even by tiny details, as shown by ‘adversarial’ results able to fool deep neural networks) from those studied at training time. While recognising this issue under different names (e.g. ‘overfitting’), traditional Machine Learning (ML) seems unable to address it in non-incremental ways. As a result, AI systems suffer from brittle behaviour, and find difficult to operate in new situations, e.g. adapting to driving in heavy rain or to other road users’ different styles of driving, e.g. deriving from cultural traits. This project reimagines AI through a proper treatment of the uncertainty stemming from our forcibly partial knowledge of the world. Epistemic AI’s paradoxical principle is that AI should first and foremost learn from the data it cannot see.

Within Computer Science, AI is dependent on data coming from sensors or networks of sensors.  However, these sensors networks suffer from calibration drifts, failures of nodes or insufficient bandwidth, etc... This causes data to be lost or to be uncertain.  In this PhD, the candidate will develop new AI-based algorithms that can cope with this uncertainty of the distributed networked system.  The candidate will apply these algorithms in automated systems, such as an automated factory (The Ultimate factory at the Bruges Campus) and automated vehicles via collaboration with the project partners.  

The research on optimisation under uncertainty will be supported by the EU H2020-FETOPEN-2018-2019-2020-01 project called Epistemic AI, an H2020-funded project due to start March 1st, 2021, coordinated by the Oxford Brooke University-UK, including KU Leuven and TU Delft as the second and third members in the project consortium. The main project goal: Epistemic AI’s overall objective is to create a new paradigm for a next-generation artificial intelligence providing worst-case guarantees on its predictions thanks to a proper modelling of real-world uncertainties.

The candidate will work on the granted 4-years EU FET-Open project (E-pi) as a part of his/her PhD. He/she will work on modelling of uncertainty and optimisation under uncertainty in AI algorithms.  The candidate will be collaborating with another PhD focussed on the mechanical aspects in this project. He/she will also contribute to other work packages for the part on facilitating the translation of these new technologies into applications. We will also assist with exploitation and dissemination, together with the other partners at the E-pi consortium (from Oxford Brooks University – UK and TU Delft – The Netherlands).

KU Leuven has a full-time PhD positions to work in the M-Group: one under Computer Science Department (CS-PhD). The successful applicant will be appointed as PhD researchers in the CS-PhD. The vacant position is located at Bruges Campus (https://www.kuleuven.be/campussen/campus-brugge) and the research activities will be embedded in the co-located Mechatronics Group (M-Group, https://iiw.kuleuven.be/onderzoek/m-group). 

Profile

  • Candidate must hold a MSc degree on Computer Science, Applied Mathematics, Industrial Engineering, Mechatronics, or equivalent degree that gives access to KU Leuven Doctoral School PhD program.
  • Candidate must be fluent in English (knowing Dutch or having a certificate for a TOEFL/IELTS test is a plus). 
  • We are seeking highly motivated, goal-oriented, individual, and pro-active candidates with a good background in (statistical) modelling, simulation, machine learning, optimisation, test (at the Ultimate Factory).
  • Experience in programming in Python, MATLAB, would be an advantage (PLC is a plus).
  • Experience in machine learning frameworks (Tensorflow, Keras, PyTorch,...) and/or distributed embedded systems is a plus.
  • Candidate must be ambitious but above all team-players and communicative.
  • The candidate will have to comply with the KU Leuven regulation on doctoral degrees (https://admin.kuleuven.be/rd/doctoraatsreglement/en/phdregulation-set) 

Offer

The PhD position has a duration of 4 years.  The candidate starts with a one-year contract and will be extended to four years after a positive evaluation. 

We offer a fully funded PhD scholarship.  You will work in a brand new campus within a young and dynamic research group. 

We also offer health insurance and mobility support. 

Interested?

For more information please contact Mr. Keivan Shariatmadar, tel.: +32 50 66 48 68, mail: keivan.shariatmadar@kuleuven.be or Prof. dr. ir. Hans Hallez, tel.: +32 50 66 48 38, mail: hans.hallez@kuleuven.be.

Please submit the following documents should you apply online:
- Curriculum vitae, showing your achievements and possible publications
- Motivation letter, clearly indicating your motivation for pursuing a PhD at the Bruges Campus of KU Leuven
- Transcripts of your Bachelor and Master studies
- TOEFL/IELTS test results or equivalent (if possible)
You can apply for this job no later than June 25, 2021 via the
KU Leuven seeks to foster an environment where all talents can flourish, regardless of gender, age, cultural background, nationality or impairments. If you have any questions relating to accessibility or support, please contact us at diversiteit.HR@kuleuven.be.
  • Employment percentage: Voltijds
  • Location: Brugge
  • Apply before: June 25, 2021
  • Tags: Industriële Ingenieurswetenschappen


If you apply for this position please say you saw it on Computeroxy

Apply

All Jobs

FACEBOOK
TWITTER
LINKEDIN

Harvard University Academic Positions

Kuwait University Current Faculty Openings

Osaka University Academic Opportunities

Purdue University Job Postings for Faculty Positions

Texas Tech University Faculty Openings

Tsinghua University Job Postings

University of Cambridge Job Openings

University of Geneva Faculty Opportunities

University of New South Wales Job Openings

University of Nottingham Research Positions

University of Oslo Academic Jobs

University of Saskatchewan Faculty Positions

University of Southampton Research Vacancies

University of Tokyo Current Academic Vacancies

University of Toronto Open Faculty Positions