Evaluating artificial intelligence: How data science and statistics can make sense of AI models

Join data scientists and statisticians from across industry and academia to debate ideas and strategies for evaluating AI.

Hosted by:

The AI Fringe

The Royal Statistical Society

Description

The Royal Statistical Society is calling for a centre for AI evaluation methodology, arguing that we should be able to judge the trustworthiness of claims made by AI companies as well as the outputs of their systems.

So, what should AI evaluation look like? How will it work in practice? What metrics are most important, and – crucially – who gets to decide this? Join us to debate these and other vital issues.

Agenda

Please note the details below are subject to changes, with more details to come.

No items found.

Speakers

Dr Andrew Garrett

President, Royal Statistical Society

Martin Goodson

Chief Executive, Evolution AI

Stephanie Hare

Researcher, broadcaster, and author of Technology is Not Neutral

Mark Levene

Principal Scientist, Department of Data Science, National Physical Laboratory

Detlef Nauck

Head of AI and Data Science Research, BT

Mihaela van der Schaar

John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine, University of Cambridge