About
Michael Tipping is Professor of Machine Learning within the Department of Computer Science at the University of Bath, where he joined in early 2016. He is a member of the Artificial Intelligence & Machine Learning research group and the Bath Institute for the Augmented Human. His work spans both theoretical and applied aspects of machine learning, with particular expertise in probabilistic modeling and Bayesian statistical approaches.
Professor Tipping's research interests center on Machine Learning and extend to Data Science and Artificial Intelligence, viewed from a probabilistic modeling and Bayesian statistical perspective. His specific research areas include Sparse Bayesian models (the "relevance vector machine") and related novel learning techniques, probabilistic approaches to tree-based pattern recognition, adaptive analysis of multivariate time series, methods for intelligent statistical automation, new perspectives on deep neural networks, and model-driven data mapping and visualisation techniques. He has maintained an interest in specific application areas including medical diagnostics, automotive modeling, payment fraud detection, sports performance analysis, and interactive entertainment.
His publication record demonstrates consistent contributions to the field since the 1990s, with particular impact in probabilistic methods. His most influential works include the Relevance Vector Machine (over 6,300 citations) and Probabilistic Principal Component Analysis (over 2,800 citations), which have become foundational techniques in Bayesian machine learning. His recent work continues to bridge theoretical advances with practical applications across diverse domains, as evidenced by his 2024 publication on underwater environment classification.
Professor Tipping has been recognized for his significant contributions to the field, with his publications being cited thousands of times across various platforms. His work on the Relevance Vector Machine has been particularly influential, offering a probabilistic alternative to Support Vector Machines with comparable performance but dramatically fewer basis functions.
With extensive industry experience including eight years at Microsoft Research (Cambridge), six years running an independent statistical consultancy, and two years as Director of Science at Cambridge analytics start-up Featurespace, Professor Tipping brings a unique perspective that bridges academic research and real-world applications. His work on the "Drivatar AI" system for Microsoft's Forza Motorsport franchise demonstrates his ability to translate advanced machine learning concepts into consumer-facing technologies.
