We are looking for a PHD researcher in explainable artificial intelligence and machine learning
The research group itec at KU Leuven, campus Kulak in Kortrijk, and imec, is looking for a PHD researcher in explainable artificial intelligence and machine learning to carry out strategic basic research.
Organizational unit
itec is a research group at KU Leuven and imec, Flanders’ high-tech research and innovation hub for nanoelectronics and digital technologies. On the campus Kortrijk of the KU Leuven, itec unites researchers from three different faculties (Psychology & Educational Sciences, Arts and Medicine) and four different disciplines (educational psychology, statistics, applied linguistics and computer science). Researchers at itec conduct both fundamental and applied research on the design, development, and evaluation of personalized and adaptive digital solutions, aimed at helping experts and end users to make effective decisions informed by data analysis and visualizations. Primary application domains include education and training, media, and health.
The main focus of the AI and machine learning subgroup of itec is to apply existing and develop new machine learning algorithms to advance the application domains. In particular, we focus on supervised, unsupervised and semi-supervised learning. Key activities in the group relate to multi-label/target prediction, recommender systems, active learning, survival analysis and longitudinal data analysis; always with a specific attention to interpretability.
Project
This PhD position will be funded by the impulse program on Artificial Intelligence (AI) Research, which is an initiative of the Flemish government to position Flanders as an international leader in the field of AI. This AI-impulse program will focus on three main pillars: strategic basic research; technology transfer & industrial applications; and supporting activities (awareness, training, ethics…). To shape the strategic basic research, a team consisting of representation of industry associations, all five Flemish Universities and all four Strategic Research Centres have worked together to define a limited number of AI Grand Challenges that are internationally recognized and for which Flanders has key R&D and domain specific strengths. This PhD position will be active in the first grand challenge of this impulse program, called Data Science: Hybrid, Automated, Trusted, and Actionable.
In particular, this PhD project will focus on interpretability towards the end user: trust and accountability are important issues in decision support systems. Especially in medical and industrial settings, such systems should preferably be interpretable. We will focus on time-to-event problems (also known as survival analysis). Standard machine learning techniques can not directly be applied to survival data, mainly because of the censoring, meaning that for some data instances, the event of interest is not measured, e.g. because of dropout or the study ended before event took place. A particular type of interpretability to consider in this context is providing actionable advice suggesting the end user which actions are expected to improve outcome. A second type is to involve the end user or domain expert to provide event times for unlabeled or censored observations that are queried by the system (active learning). We will also consider the multi-target setting, where queries can take the form of (instance, event) pairs instead of just instances, allowing a finer grained query specification.
Profile
- You have a master degree in computer science, informatics, statistics, artificial intelligence, or equivalent, with excellent (‘honors’-level) grades.
- You have followed courses related to data mining or machine learning, and show a significant enthusiasm for, and knowledge of, this domain. Be sure to mention any knowledge of (or previous experience with) time-to-event prediction, multi-target prediction or active learning.
- You are an experienced programmer in Python, R, Java or other programming languages.
- You have a strong interest in working on real applications and interacting with domain experts; you are motivated, curious and creative.
- You have excellent oral and written communication skills in English. Knowledge of Dutch will be considered an important asset.
- You are able to communicate about your work to people from another discipline.
- You are able to work independently, but also to integrate and interact with a team of fellow PhD researchers.
Offer
We offer full-time employment for a PhD researcher. Starting date is around 1 October 2019. The appointment will be for 1 year initially and will be extended after positive evaluation, subject to the continuation of the AI impulse program. The candidate will be working at the Campus Kulak in Kortrijk. (S)he will enter the doctoral program of the KU Leuven Doctoral School of Biomedical Sciences.
In addition to a competitive scholarship, KU Leuven also offers a number of additional benefits, such as hospitalisation insurance, eco-vouchers, reimbursement of commuting expenses by public transport, inexpensive meals, a KU Leuven bicycle,…KU Leuven also offers a number of additional benefits, such as hospitalisation insurance, eco-vouchers, reimbursement of commuting expenses by public transport, inexpensive meals, a KU Leuven bicycle, the possibility of flexible working…
Deadline for application: August 18, 2019