Explainable AI: Making Machine/Deep Learning models explainable

Traditional Artificial Intelligence(AI) technologies such as Machine/Deep learning used in developing intelligent/smart solutions largely rely on utilising best representative test datasets and features engineering and less on the available domain expertise. We argue that such approach to solution development makes the outcome of solutions less explainable. There is a growing concern among policy makers that with wider applicability of AI solutions in all walks of life and the lack of explainability of such solutions, it creates hindrance in acceptability and trustworthiness of such solutions. In this PhD project, the candidate will work on developing techniques and methodologies for combining Deep learning with Semantic Web technologies to make deep learning models more transparent.

The candidate will join a diverse group of researchers engaged in Artificial Intelligence, Deep Learning, Semantic Web, Smart Cities, Industry 4.0 and Internet of Things (IoT) research streams. The group members already work on world-leading research in this area in the context of funded projects (https://northsearegion.eu/score/). Candidate will have option to apply their work in a number of applied domains including: law, smart factories, smart cities, and digital health, to name a few.

Explore the work carried out by the group here: https://dthakker.wixsite.com/bradford

Eligibility:

Candidates are expected to hold (or be about to obtain) a minimum 2:1 honours degree (or equivalent) in a related area / subject, e.g. Computer Science, Data Science, Big Data, AI, IoT, Mathematics, etc. MSc, MA or relevant experience in a related discipline is highly desirable.