About the Project
This proposal is a cutting-edge investigation into explaining the decisions of commonly-used solvers for optimization problems. The PhD student will be working in partnership with British Telecom (BT), as part of a joint project also involving an already-running PhD studentship hosted by Robert Gordon University, Aberdeen. This will exploit existing expertise and collaboration between the academic and industrial partners, with the potential for a step-change advance in solving challenging industrial optimisation problems.
Explainable AI is a well-established concept, but research success in the area has mainly used methods that mimic human reasoning, making the path to solution readily understood by end-users. In non-deterministic solvers, the path to solution is driven by random processes that accumulate problem learning, as opposed to deduction from prior knowledge or experience. A description of these processes, while explanatory, is hard for non-experts to comprehend. The innovation in ENDS is to derive human-understandable knowledge about the problem from the non-deterministic solution process and translate that into an explanatory form for end-users.
The project will look at mining surrogate models to derive problem knowledge in a new way. The student will benefit from collaboration with the existing PhD studentship at RGU, which is looking at mining solution trajectories. ENDS will further innovate by expressing the problem knowledge gained via natural language generation and visualisation. End-users with no understanding of the solvers will be able to assess presented solutions in the light of a comprehensible explanation. Finally we will innovate by applying ENDS to a real world domain: workforce management at BT.
The student will be based at UoS under the supervision of Dr. Brownlee. The student will spend some time periodically at the BT research facility at Adastral Park, Ipswich, working with the BT research team and applying their research to BT datasets.
The studentship will be of 36 months duration, commencing in January 2022. The studentships is fully funded and includes Home/EU tuition fees as well as a tax-free stipend of £15,609 per annum. Non-EU students may also apply but will be required to fund the difference between Home/EU fees and International fees.
Applicants should have a first class Honours degree or a Masters at Distinction level in Computing Science or a strongly related discipline. Strong programming skills are highly desirable. Some knowledge of non-deterministic optimization algorithms, in particular population-based techniques such as genetic algorithms, is also highly desirable, though not essential. Applicants should have good personal and communication skills, strong professionalism and integrity and be confident working on their own initiative.
Applications should be emailed to Alexander Brownlee at email@example.com by 12 noon on Friday 29th October 2021. The applications should consist of a covering letter or personal statement of interest and a CV. Further information such as passport details or transcripts may be requested during the short-listing stage. Interviews will take place in mid November 2021.
Why not add a message here
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.