About the Project
We are looking for a highly motivated prospective PhD student to undergo a 3-year fully-funded PhD position in the area of machine learning and deep learning theory and applications. The appointee will join the Institute of Sensors and Signals and Systems (ISSS) in the group of Dr Marta Vallejo at Heriot-Watt University. ISSS is one of five Research Institutes in the School of Engineering and Physical Sciences and carries out a broad range of world-leading research in sensors, systems and signal processing.
The successful candidate will join the high profile EPSRC-funded “Proteus” interdisciplinary research collaboration (see: proteus.ac.uk) - a collaboration involving Heriot-Watt University, and the Universities of Edinburgh, Bath and Durham. The overarching vision of Proteus is to develop a game-changing approach to the treatment of critically ill respiratory patients using advanced microendoscopic imaging and sensing technologies to more accurately guide the care pathway.
Deep Learning theory has seen an immense development in the past few years across a number of areas in medical image analysis, such as diagnosis, registration and segmentation. However, their use in biomedicine is limited by their lack of interpretability and explainability, their unquantified robustness, and their requirements of large amounts of training data. The possible areas of interest of the position include the design of better segmentation and registration algorithms using deep learning techniques, and the development of algorithms for the extraction of biomarkers and classification. The machine learning work will also include developing methods that can explain the decision made by the models. The area of neuroevolution could be also considered.
MSc (or near completion) in Machine Learning, Artificial Intelligence or a closely related area.
• Knowledge of Machine Learning, Deep Neural Networks
• Good programming skills, preferably in Python.
• Knowledge of Tensorflow, Keras, Pytorch and/or other deep learning frameworks would be advantageous.
• Capable of working collaboratively with researchers from different disciplines
• Ability to communicate effectively both orally and in writing at a level in English appropriate to the research and presentation of data.
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.