Making AI Accessible

One of the aims of the Hub is to make important ideas from AI more accessible to a mathematical audience. The following articles give accessible introductions to different topics in AI:

An introduction to transformers. R. Turner

arXiv:2304.10557

The transformer is a neural network component that can be used to learn useful representations of sequences or sets of data-points. The transformer has driven recent advances in natural language processing, computer vision, and spatio-temporal modelling…

Denoising Diffusion Probabilistic Models in Six Simple Steps. R. Turner, C. Daiconu, S. Markov, A. Shysheya, A. Foong, B. Mlodozeniec

arXiv:2402.04384

Denoising Diffusion Probabilistic Models (DDPMs) are a very popular class of deep generative model that have been successfully applied to a diverse range….