Postdoctoral Fellowship (2 Years) within Interpretable Machine Learning

The Department of Mathematics and Mathematical Statistics is offering a postdoctoral scholarship within the project “Generative mixture of linear models by DNN co-supervision”. The scholarship is full-time for two years, with access on 1 June 2024 or by agreement.

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 organizations, military service, or similar circumstances, as well as clinical practice or other forms of appointment/assignment relevant to the subject area.

Read more and apply, by clicking the 'Apply' button

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

Advert information