A post by Compass students Ben Anson, Ollie Baker, Codie Wood and Rachel Wood.
Introduction
This October, we held our third annual Compass Conference. Unlike previous years, when the event was held in the University’s Fry Building, this time it took place at M Shed, offering scenic views of Bristol harbour. It was a great day for past and present Compass students, academics, and industry partners to come together and discuss this year’s theme: “The Future of Data Science”. With recent advances in machine learning and AI, it felt like a fitting time to learn from each other’s perspectives and to share ideas about how to move forward in this exciting space.
Student Research Talks
The morning started with four ten-minute research talks from Compass students. First was Rahil Morjaria‘s talk on “Group Testing” which explored current developments in the field, including algorithms and information-theoretic limits.
Following this, Kieran Morris presented “A Trip to Bregman Geometry and Applications”, considering advancements such as natural gradient methods, Bregman K-means clustering, and EM-projection algorithms that Bregman Geometry has enabled.
Ettore Fincato talked us through “Gradient-Free Optimisation via Integration”, focusing on a novel yet easy-to-implement algorithm for optimisation using Monte Carlo methods. Finally, Ed Milsom spoke about “Data Modalities and the Bias-Variance Decomposition”, taking us through a history of neural networks and speculating about why certain data types are so powerful, and why the future of general-purpose AI must be multi-modal.
Student Lightning Talks
The lightning talks challenged ten students to present on a topic in just three minutes. The ability to quickly convey a message in an engaging and understandable manner, to an audience with diverse backgrounds, is crucial in both academia and industry, and the students rose to the occasion.
Their talks captured the interest of the audience and inspired interesting questions that forced the students to think on their feet. Topics ranged from neural networks and large language models (LLMs), to making music using mathematics.
Compass Alumni Panel
This year’s conference panel, chaired by Compass CDT Director, Professor Nick Whiteley, offered an engaging look into the professional journeys of Compass alumni Dominic Owens, Jake Spiteri and Michael Whitehouse since completing their PhDs. With shared experiences in finance, each panelist provided unique insights into the early career landscape and the skills that helped them succeed.
Jake delved into the details of his day-to-day work in the financial sector, while Dominic discussed the challenge and dedication required to secure a role through extensive networking and job applications. Michael shared details of his transition from finance to epidemiological research. Together, they sparked valuable discussions on what the future of data science might hold for upcoming Compass graduates.
Special Guest Lecture
The conference concluded with an enlightening special guest lecture by Professor Aline Villavicencio, Director of the Institute for Data Science and Artificial Intelligence at the University of Exeter. Her talk, “Testing the Idiomatic Language Limits of Foundation Models: The Strange Case of the Idiomatic Eager Beaver in Cloud Nine,” offered a fascinating counterpoint to the current enthusiasm surrounding LLMs.
Drawing from her research in Natural Language Processing (NLP), Professor Villavicencio demonstrated how even today’s most advanced models struggle with aspects of language that humans master naturally – particularly idioms and multi-word expressions. She illustrated a persistent gap between machine and human linguistic capabilities, reminding us that the path to truly human-like language understanding remains long and complex.
She also shared her perspective on the cyclical nature of NLP research, noting how, throughout her career, there have been multiple predictions about NLP research becoming obsolete as models improve. Yet, as her work on datasets like SemEval (Semantic Evaluation) shows, there remain fundamental challenges in representing and understanding idiomatic language.
Concluding remarks
The successful day of talks, poster sessions and networking culminated with Professor Whiteley sharing his thoughts on what we learned throughout the event. He concluded that the future of our field is certain to be exciting and will encompass a huge range of different areas and ideas. This year’s conference embodied this by providing a platform for students, academics, and industry professionals to share new insights from many different sectors, and to form strong relationships to help forge a path to the future of data science.
