Are you interested in developing state-of-the-art machine learning techniques, designing new algorithms, and being prepared to take-on real-life problems involving diagnosis of Alzheimer’s? The section Business Analytics at the Amsterdam Business School  of the University of Amsterdam invites applications for a PhD position in Statistics and Machine Learning. We are looking for talented PhD candidates with the ambition to work and succeed at the highest international academic level.

What are you going to do?

The project aims to develop and apply advanced statistical and machine learning methods to facilitate the early diagnosis of Alzheimer’s disease. Since Alzheimer's is associated with brain network dysfunction, graph-based machine learning techniques are vital for disease staging and classification. Graph neural networks (GNNs) are a class of deep learning methods that have been adapted to use the structure and properties of graphs and have gained incredible success. Despite their success, these methods do not capture model uncertainty, which is crucial for the clinical assessment of Alzheimer's patients. Bayesian methods provide mathematically grounded frameworks to deal with model uncertainty but come with expensive computations.

The main objective of the PhD project is to develop computationally efficient Bayesian frameworks for GNNs.

The PhD project is divided into two parts. In the first part, we aim to develop a Bayesian framework in graphical models to capture changes in the brain network for early diagnosis of Alzheimer's by using imaging (MRI, fMRI, PET) and non-imaging (demographics and genotypes) features. The second subproject aims to improve the accuracy as well as the computation of the graph neural network (GNN) methods. We aim to introduce new types of GNNs by using the graph structure information from subproject 1. The application of this project is for the early diagnosis of Alzheimer, by classifying brain images into normal brain or brain with Alzheimer's. The newly developed methods will be applied to actual data. We have collaborations with hospitals that are in the possession of relevant data.

You will/tasks:

• develop advanced statistical and machine learning techniques, in particular, Bayesian statistical methods and graph neural networks;
• develop open-access software (R or Python package) for applying the newly developed algorithms/models and techniques to real data;
• write up findings for publication in prestigious machine learning and statistical journals;
• present research findings at leading conferences;
• attend classes and seminars (including those offered at other universities) to further develop thinking and research skills;
• participate in and contribute to departmental research functions (PhD Day, research seminars, and research meetings);
• assist in relevant teaching and knowledge dissemination activities.

What do we require?

• Master’s degree in Statistics, Mathematics, Computer Science, Artificial Intelligence, or a related discipline.
• A strong background in Modern Statistics/Machine Learning/Artificial Intelligence, including Bayesian inference and deep neural networks.
• Excellent programming skills in one or more of the following languages: R, Python, C, C++, and a strong willingness to develop these skills further.
• Excellent communication, presentation and writing skills.
• An excellent command of English, ideally with experience writing for a scientific audience.
• Commitment, perseverance and a cooperative attitude.

Our offer

The compensation package is competitive at the European level and includes several secondary benefits. Favorable tax agreements may apply to non-Dutch applicants. To know more about working at the University of Amsterdam, please check this link and uva.nl/working-at-eb.

The employment contract will be for three or four years (depending on prior education) with an initial period or 18 months, with an intermediate evaluation after 18 months and a possibility to extend it for 30 months (in total four years). End-result should be a PhD thesis. An educational plan will be drafted that includes attendance of courses and (international) conferences. The gross monthly salary will range from €2.443 in the first year to €3.122 (base on 38 hours per week) in the last year. The Collective Labour Agreement (CAO) for Dutch Universities is applicable.

What else do we offer

• A function in which your own initiative and input is strongly valued.
• an enthusiastic and warm team that is open to new colleagues.
• an inspiring academic and international work environment at the center of Amsterdam.

UvA Economics and Business

Education and research at UvA Economics and Business (EB) covers a wide range of fields that includes economics, data science, business administration, business analytics, accountancy, control, econometrics, finance and entrepreneurship. This is organised in 2 Schools: the Amsterdam Business School (ABS) and the Amsterdam School of Economics (ASE). Over 7,000 students are enrolled in our UvA Economics and Business programmes and around 500 employees provide education and support.

• Find more information about Economics and Business on uva.nl/eb.
• Find more information about the Amsterdam Business School on abs.uva.nl.
• Find more information about the Amsterdam School of Economics on ase.uva.nl.

The PhD position is with Prof. Ilker Birbil, Dr. Reza Mohammadi, and Dr. Marit Schoonhoven within the section Business Analytics at the Amsterdam Business School (University of Amsterdam). The section Business Analytics has over 30 employees who do research and teach mainly in Artificial Intelligence, Machine Learning, Statistics, Optimization, and Information Systems. The members of the department have published their research in top-tier academic journals, such as the Journal of Machine Learning Research, the Journal of American Statistical Association, and the Journal of Statistical Software. 

Members of the department are also involved in teaching in undergraduate, master, and research master level programs, as well as in executive education, and uphold strong relationships with industry, business and healthcare.