Sort by
Refine Your Search
-
(preferably neuroimaging) Computationally efficient deep learning Deep learning model generalisation techniques. Translating deep learning models to the clinic The post holder will be based in the Department
-
postdoc to work on a project funded by the Biotechnology and Biological Sciences Research Council (BBSRC). The post is for two years to study the role of the microbiome in olfaction using mouse models
-
techniques. Additional expertise in studying autophagy and using preclinical mouse models of cardiovascular disease are highly desirable. This is a full time post (35 hours per week), and you will be offered a
-
cardiovascular disease progression and outcomes. The successful candidate will work to identify key clinical and immunological predictors, develop risk models, and help generate new hypotheses to inform future
-
vitro, organoid co-culture models will be developed using primary human epithelial cells. Candidates should have an excellent research track record, be committed to the project and keen to work in a
-
Guy’s Campus, Denmark Hill and UCL. About the role: To investigate the cellular mechanisms underlying schizophrenia-related symptoms in animal models (mice), in the context of a collaborative project with
-
of liver micrometastases development in cancer, based on a novel MRI approach which combines multi-dimensional diffusion-relaxometry acquisitions, efficient data denoising and biophysical modelling
-
of Biomedical Engineering and Imaging Sciences is a cutting-edge research and teaching School dedicated to development, translation and clinical application within medical imaging and computational modelling
-
Science, Robotics, AI, or a related field 2. Strong background in machine learning and robotics, with specialisation in one or more of the following areas: generative models, reinforcement learning, human
-
better position. A model is needed into which to feed critical information and retrieve cause/effect insights on which to base logical decisions. Biological information cuts across diagnostic boundaries