Machine learning has a wide range of uses, thus concerns regarding their reliability and safety are valid. One way to ensure the properties of safety and trustworthiness of a machine learning system is to test it. Testing machine learning systems, however, is difficult due to their stochastic nature. During my PhD, I will do a detailed investigation into testing machine learning systems by applying software engineering testing approaches to achieve safe and trusted machine learning systems.
I am enthusiastic about effective research solutions for the testing of artificial intelligence systems. People’s current misconceptions about AI have eroded confidence in its capabilities, yet people need to trust that the technology will be accurate, and safe and contribute to the advancement of society. Joining the STAI CDT allows me to share my expertise, creativity and efforts to improve trust in AI. The STAI CDT differs significantly from most PhD programmes. It adds to the excitement of the PhD journey since there are a reasonable number of seminars and lectures to attend, and a student can interact with researchers and other students from a variety of AI topics. Additionally, the CDT staff provide outstanding assistance and support to students.
Undergraduate Qualification: BSc Computer Science (First Class Honours) University of Leicester
Masters Qualification: MSc Data Analytics (Distinction Level) University of Warwick
Work Experience: Teaching assistant of Mathematics Fundamentals, School of Informatics, University of Leicester (During my undergraduate degree)
Publications: 1) Property-based Testing of Quantum Programs in Q#. Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops, 2020. https://doi.org/10.1145/3387940.3391459, 2) Poster: Property-based Testing of Quantum Programs in Q#. In “15th Conference on the Theory of Quantum Computation, Communication and Cryptography (TQC 2020)”