Machine learning interpretability, explainability and trustability

We are the UK’s national institute for data science and artificial intelligence.The Institute is named in honour of Alan Turing, whose pioneering work in theoretical and applied mathematics, engineering and computing is considered to have laid the foundations for modern-day data science and artificial intelligence. The Institute’s goals are to undertake world-class research in data science and artificial intelligence, apply its research to real-world problems, driving economic impact and societal good, lead the training of a new generation of scientists, and shape the public conversation around data.Click here to join our newsletter

The Alan Turing Institute

Please only book onto this event if you plan to attend, to help us manage the space and ensure a full room.

1 Wimpole Street

The ability to interpret the predictions of a machine learning model brings about user trust and supports understanding of the underlying processes being modeled. In many application domains, such as the medical, insurance and criminal justice domains, model interpretability and explainability can be a crucial requirement for the deployment of machine learning, since a model’s predictions would inform critical decision-making. Unfortunately, most state-of-the-art models — such as ensemble models, kernel methods, and neural networks — are perceived as being complex “black-boxes”, the predictions of which are too hard to be interpreted.In this seminar, we will outline the challenges in achieving machine learning model interpretability, explainability and trustability. We will then present research progress in turning “black-box” models into “white-box” models. We also introduce key ideas on how to develop more interpretable algorithms for risk prediction, time-series prediction and treatment effects as well as how to test and communicate the goal of interpretability, explainability and trustability is achieved. We will conclude by defining the research agenda that lies ahead.18:00 - 18:30 - Registration, tea and coffee
18:30 - 18:35 - Introduction
18:35 - 19:25 - Machine learning interpretability, explainability and trustability
19:25 - 19:40 - Q&amp;A
19:40 - 20:30 - Networking receptionFind out more about our events on our <a href="http://www.turing.ac.uk/events" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">website</a>.<h3>About the speakers</h3>Mihaela van der SchaarProfessor van der Schaar is John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge and a Turing Fellow at The Alan Turing Institute in London, where she leads the effort on data science and machine learning for personalised medicine. She is an IEEE Fellow (2009). She has received the Oon Prize on Preventative Medicine from the University of Cambridge (2018). She has also been the recipient of an NSF Career Award, 3 IBM Faculty Awards, the IBM Exploratory Stream Analytics Innovation Award, the Philips Make a Difference Award and several best paper awards, including the IEEE Darlington Award. She holds 35 granted USA patents.

Sir Alan WilsonSir Alan Wilson is Director, Special Projects of The Alan Turing Institute, with responsibility for leading specific research and partnership projects. He was CEO of the Institute between 2016-2018. He is Executive Chair of The Ada Lovelace Institute, Chair of the Home Office Science Advisory Council and is a member of the Board of Directors for the Banking Standards Board.He is a Cambridge Mathematics graduate and began his research career in elementary particle physics at the Rutherford Laboratory. He turned to the social sciences, working on cities, with posts in Oxford and London before becoming Professor of Urban and Regional Geography in Leeds in 1970. He was a member of Oxford City Council from 1964-1967. In the late 1980s, he was the co-founder of GMAP Ltd, a University spin-out company. He was Vice-Chancellor of the University of Leeds from 1991 to 2004 when he became Director-General for Higher Education in the then DfES. After a brief spell in Cambridge, he joined UCL in 2007. He was Professor of Urban and Regional Systems in the Centre for Advanced Spatial Analysis at University College London up to 2018.From 2007-2013 he was Chair of the Arts and Humanities Research Council; and from 2013-2015, he was Chair of the Lead Expert Group for the Government Office for Science Foresight Project on The Future of Cities.He is a Member of Academia Europaea, an FBA, an FAcSS and an FRS. He was knighted in 2001.Notice: Please only book onto this event if you plan to attend, to help us manage the space and ensure a full room. We understand that plans change, so if you are no longer able to attend, please cancel your ticket with as much notice as possible so that someone else can book on.

Travel advice
Staff, students and visitors are asked to continue to note the latest advice and guidance on coronavirus. The Institute, alongside The British Library, is working to reduce potential risks for visitors and we are regularly reviewing official government advice.

We urge you to read the further information before attending the event. Please visit Turing's <a href="https://www.turing.ac.uk/about-us/frequently-asked-questions" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">frequently asked questions</a> and the latest government advice.

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

Machine learning interpretability, explainability and trustability

More events from The Alan Turing Institute

Discover more events from The Alan Turing Institute, from Science & Tech to other experiences you might love.

Machine learning interpretability, explainability and trustability

More events from The Alan Turing Institute

Discover more events from The Alan Turing Institute, from Science & Tech to other experiences you might love.

You might also like...

Browse more events with different dates, prices, and formats to find your next great experience.