Mathematics of Machine Learning

Machine learning (ML) is currently undergoing a massive expansion, due to the unprecedented availability of large amounts of data and computational power. The last decade has seen tremendous improvements in ML methods and achievements in many application areas including (bio-) medical sciences, computer vision and finance to name but a few.

Remarkably, while ML relies on mathematical models and tools, many ML algorithms do not have a rigorous mathematical foundation. One reason for this is that ML has been historically developed as a sub field of computer science rather than mathematics. Fundamental analysis questions are open, such as convergence and convergence rates, or the topology and geometry with which data should be studied.

It is essential that the mathematical community contributes to ML and provides a solid underpinning of ML methods. This Symposium will advocate the connection between ML and many mathematical disciplines, such as numerical analysis, inverse problems, optimisation, statistics, optimal transport, dynamical systems and partial differential equations, in order to shed light into the mysterious mathematical pathways of ML.

Call for Posters
In addition to the invited speakers, there is an opportunity for early career researchers to attend the Symposium and contribute a poster presentation. To apply, please submit a 1 page abstract here by 13th March 2020. Please note that places are limited, and notifications of acceptance will be sent out by 10th April 2020.

Please note that participants presenting a poster are responsible for their own accommodation, subsistence and travel costs. However, there is no registration fee for participation.

Further information is available from the event organisers here.

How can mathematics help us to understand the behaviour of ants? Read more about the fanscinating work being carri… View on Twitter