Training the next generation of experts in methods of safe and trusted AI
The Safe and Trusted AI PhD programme focusses on the use of symbolic AI techniques for ensuring the safety and trustworthiness of AI systems.
The Centre’s direction, training and supervision is delivered by a team of world leading experts from King’s College London and Imperial College London.
Engagement with diverse non-academic partners ensures that the Centre’s training and research are relevant and valuable to industry and society.
Cross institutional collaboration
Unique PhD opportunities
An AI system is considered to be safe when we can provide some assurance about the correctness of its behaviour, and it is considered to be trustworthy if the average user can have well-placed confidence in the system and its decision making. The Centre focusses particularly on the use of symbolic AI techniques for ensuring the safety and trustworthiness of AI systems. Symbolic AI techniques provide an explicit language for representing, analysing and reasoning about systems and their behaviours. Explicit models can be verified and solutions based on them can be guaranteed as safe and correct; and they can provide human-understandable explanations and support user collaboration and interaction with AI – key for developing trust in a system.
Cohort-based training programme
The UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence offers a unique four-year PhD programme, focussed on the use of symbolic AI techniques for ensuring the safety and trustworthiness of AI systems. Students will engage in various training activities alongside a cohort of peers, while also working on their individual PhD project. Alongside technical training in state-of-the-art AI techniques, students will acquire a deep understanding of ethical, societal, and legal implications of AI, in an academic and industrial setting.
Industry partners engage with the Centre in numerous ways including through student sponsorship, training delivery (such as group projects and hackathons), student placement opportunities and cohort building activities. This engagement ensures that students are exposed to the different experiences, challenges, and technical problems involved in both start-ups and large corporations. The training programme has been designed with input from the Centre’s partners, ensuring that the skills our students develop are relevant and valuable to industry.
Fully-funded studentships per year
Mackenzie Jorgensen presents her paper, ‘Supposedly Fair Classification Systems and Their Impacts’ at IJCAI 2022
Mackenzie Jorgensen of the 2020 cohort of the UKRI Centre for...
Elfia Bezou-Vrakatseli presents her paper ‘Towards an Argument Scheme Classification for Ethical Reasoning’ at COMMA 2022
Elfia Bezou-Vrakatseli of the 2021 cohort of the UKRI Centre for...
Paper by Jazon Szabo on ‘Integrating Quantitative and Qualitative Reasoning for Value Alignment’ contributed to EUMAS 2022
Jazon Szabo of the 2019 cohort of the UKRI Centre for Doctoral...