Connectionists: Two open PhD positions: theoretical machine learning and data-driven life science

[ISCL UU]

We are happy to announce 2 fully funded PhD positions at the Scientific Machine Learning group <https://sciml.se/>, Science for Life Laboratory (SciLifeLab) <https://www.scilifelab.se/>, Division of Scientific Computing, Uppsala University.

We are looking for highly motivated students with a strong interest in theoretical foundations of machine learning, and data-driven solutions to challenging problems in life sciences.

We appreciate enthusiasm for theoretical research in machine learning, and interest in interdisciplinary research in life sciences. We are seeking candidates with a strong background in applied mathematics, statistics, computer science, or related fields proficient in mathematical analysis, probability theory, and optimization. Solid programming skills (e.g., Python, Julia, or similar) and experience with machine learning frameworks (e.g., TensorFlow, PyTorch) are highly desirable.

Topics and application links

- Foundations of learning from noisy scientific data, with applications in inverse problems. <https://www.jobb.uu.se/details/?positionId=701936&languageId=1>
Some of the topics in the scope of this project include robust learning, variational inference, large-scale optimization, fair machine learning and Bayesian inference. There is room to discuss and explore other challenging topics in the area of theoretical machine learning as well.

We will build robust models to learn inverse mappings. Such problems often manifest as parameter inference or estimation problems (e.g., fitting mechanistic models such as gene regulatory networks to observed data) in various scientific disciplines.

Apply here <https://www.jobb.uu.se/details/?positionId=701936&languageId=1> by April 2, 2024.

- Adaptive Deep Learning for Accelerating Drug Repurposing. <https://www.math.uu.se/the-department/vacant-positions/?positionId=702358>
Together with the Pharmaceutical Bioinformatics <https://pharmb.io/> research group, we will build active learning / statistical sampling methods for optimal drug repurposing experimental design. We will develop specialised deep architectures for learning drug combination synergies to drive the sampling process. The project offers a very unique opportunity to work on challenging theoretical aspects of machine learning, in tight integration with a state-of-the-art automated robotised lab to validate the algorithms. The diseases under study include cancer (soft tissue sarcomas) and Covid.

Apply here <https://www.math.uu.se/the-department/vacant-positions/?positionId=702358> by March 22, 2024 (Project 11 <https://www.math.uu.se/digitalAssets/1078/c_1078262-l_3-k_11-singh-spjuth-adaptive-deep-learning-of-drug-combination-mechanics-for.pdf>).

Our values

We are an interdisciplinary group offering a vibrant, rich research environment with state-of-the-art resources, including computational infrastructure and collaboration opportunities within Sweden and abroad. You will enjoy a supportive and inclusive environment that values diversity, creativity, and intellectual curiosity. We offer a healthy work-life balance, and excellent career development opportunities at Uppsala University and SciLifeLab.

Please contact Asst. Prof. Prashant Singh <https://www.it.uu.se/katalog/prasi372> with any questions.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20240224/4416f8af/attachment-0001.html>