Sort by
Refine Your Search
-
Listed
-
Category
-
Employer
- Cranfield University
- ;
- ; The University of Manchester
- ; University of Leeds
- ; University of Warwick
- University of Newcastle
- ; Brunel University London
- ; Cranfield University
- ; Loughborough University
- ; Newcastle University
- ; Technical University of Denmark
- ; University of Nottingham
- ; University of Oxford
- ; University of Surrey
- Abertay University
- Imperial College London
- University of Nottingham
- University of Sheffield
- 8 more »
- « less
-
Field
-
., health and climate/environmental data) and could include a range of data science methods, such as utilising geographical information systems (GIS), statistical analysis, machine learning, deep learning
-
Cranfield University and Magdrive, offer a fully funded PhD position under the umbrella of the R2T2 consortium to study the optimisation of their thruster for a kick stage. R2T2 is a UKSA-funded
-
generation of eco-intelligent electronics that balance performance, longevity, and environmental impact. The multidisciplinary nature of this PhD ensures that students develop deep expertise in energy-aware
-
(or equivalent) in an appropriate discipline. Ideal candidate will have some prior knowledge in deep learning and computer graphics. Subject area: Medical imaging, biomedical engineering, computer science & IT
-
background in Computer Science, Mathematics. Students with interests in machine learning, deep learning, AI, uncertainty quantification, probabilistic methods are encouraged to apply. For eligible students
-
deep learning methods to enhance the predictions beyond existing data. By incorporating microstructural features into predictive models, the aim is to create a reliable data-driven modelling framework
-
through the following objectives: Develop a novel approach to investigate the fluid-solid coupling effect on the performance of the CMF; Using machine-learning (deep learning) methods to develop a
-
turbulence, and use this knowledge to identify control strategies through deep reinforcement learning. The methods developed in this project will directly contribute to designing novel porous media
-
to machine learning and deep neural networks, into the DG finite element solver to reduce computational costs while maintaining the accuracy. The key objective of this work will be to provide step-change
-
Appropriate computational skills and knowledge of programming languages (Python, C++, etc.) Experience with Machine and Deep Learning models and software (Keras, Scikit-Learn, Convolutional Neural Networks, etc