Postdoctoral fellowship (2 years) within interpretable machine learning

Project description

Artificial intelligence (AI) has become ubiquitous in our daily lives even though we are often not aware of the technology being in action. Machine learning (ML) is an area at the technical core of AI. With the enormous success of deep neural networks (DNN), the research focus of ML has shifted from pursuing high accuracy to a few other qualities of an ML system. One of the highly valued traits of an ML system is interpretability. For some critical tasks, a black-box ML classifier is rejected even if it performs the best on a test dataset. The caution against black-box ML is well grounded since a test dataset usually cannot fully represent the phenomenon under study. For proof of concept, we have developed a prototype approach to approximate the prediction of a DNN model by a piecewise linear function (or linear decision boundaries) called Mixture of Linear Models (MLM).

This project aims to further develop MLM by incorporating more sophisticated region-specific models and enhancing the training of the modules in MLM. These improvements will expand the potential applications of the method and increase prediction accuracy. This project will contribute novel algorithms for interpretable ML and create a platform for a formal study of the relationship between interpretability and prediction accuracy.

The successful candidate will be part of the research group on statistical learning and inference for spatiotemporal data at the Department of Mathematics and Mathematical Statistics at Umeå University, which closely cooperates with the Department of Statistics at Penn State University, USA. You will be given the excellent opportunity to work within the research environment conducting machine learning and AI research at Umeå University to develop your scientific qualifications.

The scholarship holder will be based at the Department of Mathematics and Mathematical Statistics in Umeå and financed by the Kempe Foundations.

Qualifications

To qualify as a postdoctoral scholarship holder, the postdoctoral fellow must have completed a doctoral degree or a foreign degree deemed equivalent to a doctoral degree in mathematical statistics, machine learning or equivalent academic competence. This qualification requirement must be fulfilled by the time of the decision about the scholarship recipient.

Priority should be given to candidates who completed their doctoral degree three years prior, according to what is stipulated in the paragraph above. If there are special reasons, candidates who completed their doctoral degree prior to that may also be eligible. Special reasons include absence due to illness, parental leave, appointments of trust in trade union organisations, military service, or similar circumstances, as well as clinical practice or other forms of appointment/assignment relevant to the subject area.

Documented knowledge and experience in modern statistical learning, deep learning, and interpretable machine learning are required. Good communication skills in spoken and written English are required. Good programming skills are merits.

The research tasks require great independence, accuracy, and dedication. Documented scientific momentum and the ability to work independently as well as part of a research group are merits. An excellent publication track record and experience in interpretable machine learning are strong merits.

Application

A complete application should include:

• Cover letter in which you describe your qualifications, your research interests, and how they relate to the advertised project (max three pages),
• Curriculum vitae (CV) with publication list,
• Verified copy of doctoral degree certificate or documentation that clarifies when the degree of doctor is expected to be obtained,
• Verified copies of other diplomas, list of completed academic courses and grades,
• Copy of doctoral thesis and relevant articles,
• Other documents that the applicant wishes to present,
• Contact information to two persons willing to act as references.

Submit your application as a PDF marked with the reference number FS 2.1.6-888-24, both in the file name and in the subject field of the email, to medel@diarie.umu.se. The application should be written in English. Application deadline is 7 June 2024. 

Umeå University strives to offer an equal environment where open dialogue between people with different backgrounds and perspectives lays the foundation for learning, creativity, and development. We welcome people with diverse backgrounds and experiences to apply for this scholarship, especially encouraging female applicants.

More information

Further details are provided by Professor Jun Yu, jun.yu@umu.se and Professor Jia Li, jol2@psu.edu.

More information about the department: https://www.umu.se/en/department-of-mathematics-and-mathematical-statistics/.

We look forward to receiving your application.