https://spinorial.net/tags/topological-deep-learning/ Recent content in Topological Deep Learning on Eric O. Korman Hugo en-us Wed, 30 Jun 2021 00:00:00 +0000 https://spinorial.net/posts/tdl-rl/ Wed, 30 Jun 2021 00:00:00 +0000 https://spinorial.net/posts/tdl-rl/ In this post we cover two papers that apply topological deep learning to three flavors of representation learning: autoencoders, self-supervised learning, and metric learning. https://spinorial.net/posts/tdl/ Sat, 02 Jun 2018 00:00:00 +0000 https://spinorial.net/posts/tdl/ <p>This is the first in a series of posts merging ideas from topology with current techniques of machine learning (such as deep generative models). Here we give an introduction to topology and discuss why it is a useful framework for data science. Subsequent posts will go into more technical detail and describe various applications.</p> <h2 id="what-is-topology">What is topology?</h2> <p><em>Topology</em> is the mathematical discipline that studies shape, with a fairly lenient notion of what it means for two shapes to be the “same.” To get a feeling for topology, it is useful to contrast it with its more familiar cousin, <em>geometry</em>. In geometry, two shapes are considered the same up to rigid motion: picking up a triangle and rotating or moving it to a different location does not change its shape.</p>