Unlocking AI for 360° spherical data — While AI is now commonplace for standard types of data, such as structured, sequential and image data, the application of AI is severly curtailed for other more complex forms of data. These more complex datasets typical exhibit non-trivial geometry. The field of geometric AI, or geometric deep learning, has emerged…

AI for complex data — Deep learning is hard. While universal approximation theorems show that sufficiently complex neural networks can in principle approximate “anything”, there is no guarantee that we can find good models. Great progress in deep learning has nevertheless been made by judicious choice of model architectures. These model architectures encode inductive biases…

Geometric AI allows you to step inside 360° VR photos and videos — Today’s virtual reality (VR) experiences fall short of the realism users expect. Current VR technology essentially falls into two categories: those based on 3D models with computer generated imagery (CGI); and those based on panoramic 360° imagery. CGI-based experiences are interactive and support novel views but are far from photorealistic…

Machine learning assisted computation of the marginal likelihood — Bayesian model comparison provides a principled statistical framework for selecting an appropriate model to describe observational data, naturally trading off model complexity and goodness of fit. However, it requires computation of the Bayesian model evidence, also called the marginal likelihood, which is computationally challenging. …

Hybrid rotationally equivariant spherical CNNs — Notions of spherical convolution offer a promising route to unlocking the potential of deep learning for the variety of problems in which spherical data are prevalent. However, the introduction of non-linearity is a challenge. In this post we explore how ideas originating in quantum physics may be applied to overcome…

Spherical CNNs By encoding an understanding of the translational symmetry of the physical world, convolutional neural networks (CNNs) have revolutionised computer vision. …

How geometric AI techniques can be used to alleviate cybersickness — Today’s 360° virtual reality (VR) experiences have great potential, allowing you to be transported anywhere in the world. They are photo-realistic and relatively easy and cheap to acquire — requiring only an off-the-shelf 360° camera — but they lack immersion and interactivity. …

How to ace your PhD application interview and land that dream PhD position. — It’s that time of year when prospective PhD students are interviewing for PhD positions to start next academic year. Over the past week I’ve interviewed around 40 prospective students. Every year the calibre of applicants just seems to get better and better. I’m continually amazed by all of the cool…

Harnessing symmetry in machine learning — In many ways physics and machine learning share a common goal: to formulate models of observed phenomena. In achieving this goal physicists have long understood the importance of symmetry. …