Skip to content
What's on

How and when will machines be able to explain themselves?

Event

Location

The ExCeL Centre

Overview

“Show your working” is a phrase that’s drilled into every maths pupil from an early age, but why do we never ask our computers to do the same?

Image © Kirillm

Machine learning has led to computers designing their own algorithms that can complete incredibly complex tasks previously thought to only be solvable by humans – from spotting a piece of spam mail to beating the world’s leading Go player. However, when we look under the bonnet of how these algorithms are put together, computer scientists are unable to gain any insight as to how the computer arrived at its solution.

Join our expert panel of machine learning specialists – Joanna Bryson, Miranda Mowbray and Stephen Roberts - who will discuss how we might go about understanding the thought-process of a machine learning algorithm.

This event is part of the New Scientist Live 2016.

For all enquiries, please contact events@royalsociety.org

How and when will machines be able to explain themselves?

Machine learning has led to computers designing their own algorithms that can complete incredibly complex tasks previously thought to only be solvable by humans – from spotting a piece of spam mail to beating the world’s leading Go player. However, when we look under the bonnet of how these algorithms are put together, computer scientists are unable to gain any insight as to how the computer arrived at its solution.

other
Was this page useful?
Thank you for your feedback
Thank you for your feedback. Please help us improve this page by taking our short survey.