The project addresses the fundamental question of how to trust a neural network that controls a dynamical system. Since neural networks are large black boxes, we need both automatic methods to analyze such systems and human-interpretable certificates of the analysis results. We will devise automatic and sound methods to respectively certify correctness and incorrectness of neural-network controllers. We will also develop a framework that integrates these methods for constructing correct-by-design controllers. Methodologically, we shall investigate how traditional computer-science techniques for verification and falsification as well as machine learning can be tailored to these goals. This way, the project lays the grounds toward safe AI control systems.
The selected candidate will be part of the Distributed, Embedded and Distributed Systems research group: https://www.cs.aau.dk/research/distributed-embedded-intelligent-systems/
Applicants must have a Master’s degree in computer science or a closely related field. Due to the project’s angle, applicants should have a strong background in at least one of the following areas: formal methods, machine learning. Additional knowledge and experience within the following areas are appreciated: formal verification, deep learning, dynamical systems, control theory. Excellent spoken and written communication skills in English are expected.
An application must contain:
1. A cover letter of max. 2 pages(excl. references), including(i) motivation for applying,(ii) preferred starting date, and(iii) an explanation of the applicant’s background and suitability for the position
2. A CV
3. A diploma and transcripts of records
4. Other relevant information, including contact information of references
Please note: If encountering a prompt in the online submission system, requesting a project description, please upload a blank file, alternatively copy of this job advertisement.
Interested applicants are encouraged to contact Assistant Professor Christian Schilling (email@example.com) and Professor Kim Guldstrand Larsen (firstname.lastname@example.org) regarding the scientific aspects of the position.
Shortlisting will be applied. This means that, subsequent to the deadline for applications, the head of department supported by the chair of the assessment committee will select candidates for interview. All applicants will be informed whether they will be interviewed or not. Interviews are planned to be held at the beginning of March.
PhD stipends are allocated to individuals who hold a Master's degree, normally for a period of 3 years. It is a prerequisite for allocation of the stipend that the candidate will be enrolled as a PhD student at the Technical Doctoral School of IT and Design in accordance with the regulations of Ministerial Order No. 1039 of August 27, 2013 on the PhD Programme at the Universities and Certain Higher Artistic Educational Institutions. According to the Ministerial Order, the progress of the PhD student shall be assessed at regular points in time.
For further information about stipends and salary as well as practical issues concerning the application procedure, please contact Ms. Annemarie Davidsen, the Doctoral School at The Technical Faculty of IT and Design, email: email@example.com
For more information on the Department of Computer Science: www.cs.aau.dk
For more information of The Technical Doctoral School of IT and Design: www.phd.tech.aau.dk
The application is only to be submitted online by using the"Apply online" button below.
AAU wishes to reflect the diversity of society and welcomes applications from all qualified candidates regardless of personal background or belief.
Wages and employment
Appointment and assessment process