-
modalities (biological, clinical/pathological data and medical imaging), with an emphasis on developing interpretable and biologically meaningful models . Methods include machine/deep learning, image
-
deep learning (e.g. generative models, Bayesian deep learning or large pre-trained models) and excellent programming skills in Python and a modern deep learning framework (e.g., PyTorch or JAX) are
-
biology, protein engineering, biochemistry. Building quantitative models: Using high-throughput binding data to build sequence dependent predictive deep learning models, and physical mechanistic models
-
obtained earlier. The three-year period can be extended due to circumstances such as sick leave, parental leave, duties in labour unions, etc. Documented experience in machine learning, in particular deep
-
learning for intelligent transportation infrastructure and systems. Experience and expertise in human mobility simulation and prediction with agent-based modeling and deep learning techniques. Proficient
-
interpretable machine-/deep-learning models. Publish research results in high-quality international journals (at least two peer-reviewed papers are expected). Eligibility Appointment to a postdoctoral
-
. On the computational side, the doctoral student will apply and further develop state-of-the-art deep learning and reinforcement learning approaches for protein design. On the experimental side, the
-
computational component and will include advanced deep learning methods for image analysis and genomic data integration to identify molecular programs associated with different functional cell states