Interpretability, safety and security in AI

Workshop theme

This conference will overview the state-of-the-art within the wide area of trustworthy artificial intelligence including machine learning accountability, fairness, privacy, and safety; it will overview emerging directions in trustworthy artificial intelligence, and engage with academia, industry, policy makers, and the wider public.

The conference consists of two parts:

1) Academic-oriented event - Monday 13 December (10:00 - 16:45 GMT)

2) Public-oriented event - Tuesday 14 - Wednesday 15 December (12:00 - 18:00 GMT)

This is a virtual conference and will be hosted on Zoom. Details about registration are available here

Speakers

Dr Hannah Fry (Professor in Mathematics at UCL, Author, and Radio, Television and Podcast Presenter)
Professor Stuart Russell (Professor of Computer Science at University of California, Berkeley)
Dr Cynthia Dwork (Honorary Fellow and Gordon McKay Professor of Computer Science, John Paulson School of Engineering and Applied Sciences at Harvard University)
Professor Mihaela van der Schaar (Turing Fellow, John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge and Founder and Director of the Cambridge Centre for AI in Medicine)
Professor Yonina Eldar (Professor of Electrical Engineering, Weizmann Faculty of Mathematics and Computer Science Dorothy and Patrick Gorman Professorial Chair Head of Biomedical Engineering and Signal Processing Center at Weizmann Institute of Science)
Professor Aleksander Madry (Cadence Design Systems Professor of Computing at MIT)
Professor Curtis Langlotz (Professor of Radiology and Biomedical Informatics at Stanford University)
Professor Cynthia Rudin (Professor of Computer Science at Duke University)
Professor Emmanuel Candes (Professor of Mathematics and of Statistics and Professor of Electrical Engineering at Stanford Universit)
Professor Desmond Higham (Professor of Numerical Analysis at University of Edinburgh School of Mathematics)
Professor Manuela Veloso (Head of J.P. Morgan Chase AI Research and Herbert A. Simon University Professor at Carnegie Mellon University)
Professor Marta Kwiatkowska (Professor of Computer Systems, University of Oxford)
Professor Isaac Kohane (Marion V. Nelson Professor & Chair at the Department of Biomedical Informatics, Harvard Medical School)
Professor Bin Yu (Scientific Advisory Board Member and Chancellor's Professor in the Departments of Statistics and of Electrical Engineering & Computer Sciences at the University of California, Berkeley)
Dr Pushmeet Kohli (Head of AI for Science at DeepMind)
Professor Ben Adcock (Professor of Mathematics at Simon Fraser University)

The application is closed

Timetable

Monday 13th December 2021
11:00 to 11:10	Introduction	No Room Required
11:10 to 12:10	Yonina Eldar Weizmann Institute of Science Model based deep learning: Applications to imaging and communications	No Room Required
12:10 to 13:10	Pushmeet Kohli Microsoft (UK) Towards Safe, Reliable and Trustworthy AI	No Room Required
13:10 to 14:10	Break	No Room Required
14:10 to 15:10	Des Higham Instabilities in Deep Learning	No Room Required
15:10 to 15:30	Break	No Room Required
15:30 to 16:30	Ben Adcock Simon Fraser University TBA	No Room Required
16:30 to 17:30	Bin Yu University of California, Berkeley TBA	No Room Required
17:30 to 17:45	Wrap up	No Room Required

Tuesday 14th December 2021
12:00 to 12:05	Introduction	No Room Required
12:05 to 13:05	Mihaela van der Schaar University of Cambridge Machine learning in healthcare: Interpretability, explainability and trustworthiness	No Room Required
13:05 to 14:05	Cynthia Rudin. Scoring systems: At the extreme of interpretable machine learning	No Room Required
14:05 to 14:30	break	No Room Required
14:30 to 15:30	Isaac Kohane. Active human-machine interactions necessary for interpretability	No Room Required
15:45 to 16:45	Curt Langlotz. Preserving patient safety as AI transforms clinical care	No Room Required
16:45 to 17:45	Emmanuel Candes Stanford University TBA	No Room Required
17:45 to 18:00	Wrap up	No Room Required

Wednesday 15th December 2021
12:00 to 12:05	Introduction	No Room Required
12:05 to 13:05	Marta Zofia Kwiatkowska University of Oxford TBA	No Room Required
13:05 to 14:05	Cynthia Dwork Microsoft (UK) Algorithmic Fairness and Individual Probabilities	No Room Required
14:05 to 14:30	Break	No Room Required
14:30 to 16:00	Panel session. Cynthia Rudin, Manuela Veloso, Isaac Kohane, Aleksander Madry, Hannah Fry	No Room Required
16:30 to 17:30	Stuart Russell. Human-compatible artificial intelligence	No Room Required
17:30 to 17:45	Wrap up	No Room Required

Organisers

Anders Hansen University of Cambridge

Speakers

Ben Adcock Simon Fraser University
Emmanuel Candes Stanford University
Cynthia Dwork Microsoft (UK)
Yonina Eldar Weizmann Institute of Science
Des Higham
Pushmeet Kohli Microsoft (UK)
Marta Zofia Kwiatkowska University of Oxford
Mihaela van der Schaar University of Cambridge
Bin Yu University of California, Berkeley