Sort by
Refine Your Search
-
Category
-
Employer
- Chalmers University of Technology
- SciLifeLab
- Umeå University
- Linköping University
- Swedish University of Agricultural Sciences
- Lulea University of Technology
- Mälardalen University
- Jönköping University
- University of Lund
- Blekinge Institute of Technology
- Nature Careers
- Uppsala University
- 2 more »
- « less
-
Field
-
and accepted to the PhD program at Stockholm University. Project description Project title: “Deep learning modeling of spatial biology data for expression profile-based drug repurposing”. A new exciting
-
, you must have: A master's degree corresponding to at least 240 higher education credits in Engineering Physics (F) or Electrical Engineering (E); good communication skills; the ability to work in an
-
Aluminium through Machine Learning, High-Throughput Microanalysis, and Computational Mechanics” - a multidisciplinary research effort at the intersection of machine learning and materials science. This
-
, dynamic programming , statistical signal processing, reinforcement learning, and have good programming skills in Python and MATLAB. - Ability to work independently and ability to formulate and tackle
-
environments.DutiesThe PhD student will carry out research in the area of cooperative autonomous systems. The successful candidate will explore topics such as: Multi-agent reinforcement learning Distributed control
-
areas, engaging in both theoretical and experimental research in: Data-driven and learning based control - Data-driven adaptive motion planning - Cognitive reasoning, symbolic knowledge representation
-
the molecular level. While structural predictions using deep learning methods like AlphaFold have revolutionized our understanding of sequence dependent molecular structure, we currently have much more limited
-
. The long-term goal is to enable targeted interventions for the right individuals, based on their lifestyle, disease trajectories, and molecular profiles. To achieve this, we will apply deep learning models
-
, implementation of methods in computer codes, use of state-of-the-art high-performance computers in Sweden and in Europe, application of machine-learning and AI techniques, and collaborations with experimental
-
will use machine learning methods to develop affinity ligands. These methods have been transformative for protein design, allowing generation of novel proteins which can suit a precise need. In this 4