Sort by
Refine Your Search
-
developing cutting-edge computer vision and deep learning aimed at optimising inspection and monitoring of infrastructure. Applying these advanced technologies to real-world infrastructure challenges through
-
developing cutting-edge computer vision and deep learning aimed at optimising inspection and monitoring of infrastructure. Applying these advanced technologies to real-world infrastructure challenges through
-
Bayesian methods, deep learning, deep generative models, reinforcement learning, graph neural networks. Interviews are expected to happen in July 2025. Applicants are encouraged to guarantee that referees
-
Bayesian methods, deep learning, deep generative models, reinforcement learning, graph neural networks. Interviews are expected to happen in July 2025. Applicants are encouraged to guarantee that referees
-
modern Bayesian modelling frameworks such as Stan, Turing.jl, and PyMC, including automatic differentiation frameworks, MCMC sampling algorithms, and iterative Bayesian modelling. Special attention will be
-
areas, and be able to creatively combine disciplines to make new research advances in fluid mechanics. You will be creating data-driven algorithms which can solve state estimation problems in fluid
-
-driven algorithms which can solve state estimation problems in fluid mechanics, such as inferring the instantaneous state of a fluid’s velocity field from sensors embedded in its boundary. The research
-
, and Internet-of-Things / Industry 4.0 technologies. Knowledge of computer science principles and modern AI approaches in computer vision and/or time series analysis is a plus. The position requires
-
aligned with the objectives of the CCGE. These include cancer risk estimation and the investigation of the genetic and clinical epidemiology for genetically susceptible individuals. This role is ideally
-
emissions, and enhance occupant health and wellbeing. As a Research Assistant, you will work closely with UK- and Egypt-based teams to analyse collected data, develop and test computer-based retrofit models