Machine learning is a driver of the current resurgence of artificial intelligence and is playing increasingly important roles in some computer systems in our daily lives. Machine learning is typically entirely data driven; thus, it has some limitations. One limitation is the lack of an ability with a traditional machine learning system to explain its outputs, which has fuelled recent research in explainable AI. Another limitation is the lack of an attention facility to solve well known problems such as the “cocktail party problem”, which has motivated recent research in attention mechanisms in deep learning.
This project will study knowledge-based machine learning, i.e., both knowledge and data are used in the process of machine learning, where knowledge provides the model structure and data determines the model parameters. The knowledge may be guidelines, domain ontologies, or characterisation of objects. It is expected that a knowledge-based learning system will have innate capabilities for explanation and attention.
This project provides an opportunity to combine cutting edge research at the intersection of knowledge and machine learning to address the above key challenges. The timeliness of this PhD project becomes also apparent in the potential of the above integration to contribute to the long-standing goal of explainable and interpretable AI.
This project will investigate fundamental research questions about knowledge-based learning and will be guided by various application scenarios where rich domain knowledge exists:
Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.
We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.
In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University offers the following levels of support:
The following scholarship options are available to applicants worldwide:
These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) to help support the PhD researcher.
Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.
Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).
This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.
Due consideration should be given to financing your studies. Further information on cost of living
Submission deadline
Friday 5 February 2021
12:00AM
Interview Date
Week Beginning 22nd March 2021
Preferred student start date
Mid-September 2021
Telephone
Contact by phone
Email
Contact by email