Newsletter Issue - 16-03-2026

CDT Weekly Newsletter


Welcome to this week’s issue of the newsletter.



Keynotes LIVE talk: The why and how of classifier calibration given by Peter Flach 


Time: 15:00 - 16:00

Location: Pugsley Lecture Theatre, Queens Building 

Title: The why and how of classifier calibration 

Abstract: In machine learning, a well-calibrated classifier correctly quantifies the level of uncertainty or confidence associated with its instance-wise predictions. This is essential for critical applications, optimal decision making, cost-sensitive classification, and for some types of context change. Peter will survey the main concepts and methods, including proper scoring rules and other evaluation metrics, visualisation approaches, and post-hoc calibration methods for binary and multiclass classification. 

Bio: Peter Flach is Professor of Artificial Intelligence in the School of Computer Science at the University of Bristol and was already doing AI long before it became fashionable. Over the years, his research has focused on mining highly structured data, the evaluation and improvement of machine learning models, and interpretable, human-centred AI. Peter is Director of the UKRI AI Centre for Doctoral Training in Practice-Oriented Artificial Intelligence, and was founding Director of the preceding UKRI CDT in Interactive AI. 



Forthcoming Calendar of Events



CDT AI Symposium – Foundation and Applications of Trustworthy AI