with TU Delft and KU Leuven as partners.

The project���s overarching objective is to develop a new paradigm for a next-generation artificial intelligence providing worst-case guarantees on its predictions thanks to a proper modelling of real-world uncertainties. The project re-imagines AI from the foundations, with the aim of providing a proper treatment of the ���epistemic��� uncertainty stemming from a machine���s forcibly partial knowledge of the world by means of advanced uncertainty theory.��
��
In particular, the work will focus on employing uncertainty measures (such as non-additive probabilities and random sets) to ���robustify��� statistical learning and unsupervised learning (e.g. by generalising generative adversarial networks), create a robust theory of supervised learning (e.g. by devising suitable loss functions for random sets and convex sets of probabilities) and propose an epistemic reinforcement learning framework by reformulating sequential decision making under second-order uncertainty. The new epistemic learning paradigms will be validated in the autonomous driving application scenario.
��
The Visual Artificial Intelligence Laboratory is a fast-growing research unit currently running on a budget of ��3.2 million from nine live projects funded by the EU (2), Innovate UK (2), Leverhulme, EPSRC and others. http://cms.brookes.ac.uk/staff/FabioCuzzolin/
��
We are leaders in the field of deep learning for action detection, but our research interests span artificial intelligence, uncertainty theory, machine learning, computer vision, autonomous driving, surgical and mobile robotics, AI for healthcare. The Lab is currently pioneering frontier topics in AI such as machine theory of mind, self-supervised learning, continual learning and future event prediction. The Laboratory is part of the University���s new Institute for Ethical AI and is in the process of launching a new start-up to develop the world���s first AI-powered coaching app for competitive sports.
��
You will join a vibrant and fast growing team foreseen to comprise 35+ people in 2022. You will support Prof Cuzzolin in the overall management of the project, and will be assisted by another research fellow and two PhD students on the project. You will be working on a network of cutting edge 4-GPU and 8-GPU workstations, mentor PhD and MSc students and seek additional external funding to complement the Lab���s existing activities.
��
You are encouraged to contact Prof Cuzzolin at fabio.cuzzolin@brookes.ac.uk for more information and an informal feedback on your application.
��
To apply, please follow the instructions you can find here: