You can find lots of information on Kaggle about competing, but it is difficult to know what is relevant and also very expensive in terms of time and effort – so we put all the essential knowledge into one book. Konrad: My favorite part is Chapter 12 on simulation competitions. Reinforcement learning is a field I have been getting into over the last few years – unlike computer vision or NLP, it has yet to reach wider appeal outside academic circles. It was an interesting and educational experience to try and distill what I have learned into a useful introduction to that fascinating domain. Luca: I enjoyed writing about the history of Kaggle and the professional opportunities it offers.

If there are any problems, you should be able to just reload the page. The code and notebooks are in a GitHub repo. The video is here YouTube.

We provide a general mathematical framework for group and set equivariance in machine learning. We define group equivariant non-expansive operators (GENEOs) as maps between function spaces associated with groups of transformations. We study the topological and metric properties of the space of GENEOs to evaluate their approximating power and set the basis for general strategies to initialize and compose operators. We define suitable pseudo-metrics for the function spaces, the equivariance groups and the set of non-expansive operators. We prove that, under suitable assumptions, the space of GENEOs is compact and convex.