Artificial intelligence and deep learning: Your questions answered

Artificial intelligence, machine learning, deep learning – these ideas now frequently appear in the news, are part of important debates in government, and a growing discussion in wider society. We all need to know what they mean so we too can be part of the conversation.

To find out more we spoke to Chris Budd and Yury Korolev from the University of Bath, and Kweku Abraham from the University of Cambridge. They are all researchers in this area and are members of the Maths4DL (mathematics for deep learning) research project. Here is what we learned.

What is artificial intelligence? – Artificial intelligence (AI) is an umbrella term for a large set of ideas revolving around reasoning by non-living objects, such as computers. Find out more in this article.

What is machine learning? — One of the most significant developments in artificial intelligence, where rather than teaching a machine explicitly how to do a complex task (in the sense of a traditional computer program), instead the machine learns directly from the experience of repeatedly doing the task itself. Find out more in this article.

What is deep learning? — Deep learning is a particular type of machine learning where an iterative process of transforming the inputs is used to recognise structures in the raw input data. Find out more in this article.

 

About this FAQ

This FAQ was written by Rachel Thomas and Marianne Freiberger, with Kweku Abraham, Chris Budd and Yury Korolev.

Kweku Abraham is a postdoctoral researcher in statistics at the University of Cambridge, working on the mathematics of deep learning.

Chris Budd is based at the University of Bath, where he is Professor of Applied Mathematics. He is also Professor of Maths at the Royal Institution and Gresham Professor of Geometry. He has also been the Education Officer of the London Mathematical Society, and Vice-President of the Institute of Mathematics and its Applications.

Yury Korolev is a Lecturer in Mathematics and Data Science and an EPSRC Postdoctoral Fellow at the Department of Mathematical Sciences at the University of Bath, and a Quondam Fellow of Hughes Hall, University of Cambridge.

Marianne Freiberger and Rachel Thomas are Editors of Plus.

This content was produced as part of our collaboration with the Mathematics for Deep Learning (Maths4DL) research programme. Maths4DL brings together researchers from the universities of Bath and Cambridge, and University College London and aims to combine theory, modelling, data and computation to unlock the next generation of deep learning. You can see more content produced with Maths4DL here.