Machine Learning in a Non-Euclidean Space

<h2><strong>What you will learn in this article.</strong></h2> <p>1. There are different examples of non-Euclidean geometry, among them&nbsp;<strong>spherical geometry</strong>&nbsp;and&nbsp;<strong>hyperbolic geometry</strong>.</p> <p>2. A hyperbolic space is a space of&nbsp;<strong>negative constant curvature</strong>.</p> <p>3. There are different models of hyperbolic geometry, the most famous being the&nbsp;<strong>Poincar&eacute; ball model</strong>.</p> <p>4. For datasets with a hierarchical structure, it is better to represent it in a hyperbolic space, because&nbsp;<strong>both a hyperbolic space and a hierarchical dataset have an inherent exponential growth.</strong></p> <p><a href="https://medium.com/towards-artificial-intelligence/machine-learning-in-a-non-euclidean-space-8f3d13f0a317"><strong>Read more</strong></a></p>