The University of Southampton

×

Email:: je5g15@ecs.soton.ac.uk

Joseph Early

Personal homepage

Joseph is a doctoral student with the University of Southampton and the Alan Turing Institute. He completed an undergraduate degree in computer science at the University of Southampton, and then specialised with a master’s degree focused on machine learning (also at the University of Southampton). Joseph pursed his interest in machine learning and is now researching explainable artificial intelligence – the process of unpacking the “black box” of machine learning and understanding why models exhibit certain behaviours.

Joseph is motivated by the possibility for collaboration within the Turing, with a strong interest in helping others apply and understand machine learning in their domains. He believes a drive towards openness, transparency and explainability in artificial intelligence will allow the recent advances in machine learning to spread and contribute to other areas such as medicine and urban analytics.

Joseph also has experience working in the start-up industry. Using his specialist machine learning knowledge, he contributed to a start-up within the University of Southampton during his master’s degree. He is excited to see how the field of artificial intelligence will progress in the future and is looking forward to working alongside other researchers from a diverse range of fields.

Research

Research interests

Joseph’s doctoral research primarily focuses on explainable artificial intelligence. With the recent rise and successes of deep learning, increasing concern has been raised over the “black box” nature of modern machine learning models and the lack of understanding around how they make predictions. Explainable artificial intelligence represents a drive towards open, transparent and fair models that are easily interpretable. Through analysis of models and data, explainable artificial intelligence can be used to expose bias and shine the light on the inner workings of machine learning.

Beyond the main scope of his research, Joseph is interested in additional machine learning areas such as reinforcement and unsupervised learning. He also maintains an interest from his undergraduate dissertation in genetic algorithms. Beyond machine learning, Joseph is looking to achieve strong collaboration with those interested in applying artificial intelligence to their own research. He is particularly interested in contributing to domain-specific research projects where explainable artificial intelligence is required, as well as developing tools to help researchers explain their machine learning models.

Publications

Early, Joseph, Evers, Christine and Ramchurn, Sarvapali (2022) Model agnostic interpretability for multiple instance learning. International Conference on Learning Representations 2022. 25 - 29 Apr 2022. 25 pp .

Reed, Chris, Grieman, Keri and Early, Joseph (2021) Non-asimov explanations regulating AI through transparency. Nordic Yearbook of Law and Informatics. (doi:10.48550/arXiv.2111.13041).

Contact

Email: je5g15@ecs.soton.ac.uk

Share this profile Facebook Twitter Weibo