Categorical Deep Learning

The second in a two-lecture series on our recently-announced Categorical Deep Learning framework (), given as a lecture for the Geometric Deep Learning (GDL) course at Cambridge. It presents how Categorical Deep Learning generalises GDL using the constructs introduced previously, and offers a discussion into ways in which its contributions can extent from semantics into syntax. Assumes prior knowledge of basics of geometric deep learning, as well as the previous lecture (Into the Realm Categorical).