Postdoc in Machine Learning using Tensor Networks - DTU Compute
Are you interested in developing novel machine learning methodologies that are scalable, reliable and explainable and that can address imminent challenges both within quantum physics and the life-sciences?
A Tensor Network (TN) is a data structure for representing high-dimensional arrays (tensors) in a low-rank format as a sequence of smaller cores which can be stored and manipulated efficiently. TNs provide promising tools for large-scale machine learning, as they allow for exponential savings in memory and processing time, while often allowing for explainable structure extraction. However, key obstacles remain, preventing their widespread use. These include limitations in terms of reliable large-scale inference, uncertainty quantification, as well as efficient TN structure identification, assessment, and interpretation. You will address these obstacles and demonstrate how the developed tools can address important challenges within quantum physics as well as large-scale life-science data modeling.
You will be supervised by Professor Morten Mørup at DTU Compute, Section for Cognitive Systems and also closely collaborate with Prof. Rasmus Bro and Assoc. Prof. Michael Kastoryano at the University of Copenhagen Department of Food Science and Department of Computer Science respectively. The position is financed by the Novo Nordisk Foundation Data Science Collaborative Grant “Tensor Networks for Data Science”.
Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply now", fill out the online application form, and attach all your materials in English in one PDF file. The file must include:
Applications received after the deadline will not be considered.
|
Apply