no code implementations • 28 Jul 2021 • Mario Alvarez-Picallo, Dan R. Ghica, David Sprunger, Fabio Zanasi
We enhance the calculus of string diagrams for monoidal categories with hierarchical features in order to capture closed monoidal (and cartesian closed) structure.
no code implementations • 9 Oct 2020 • David Sprunger
Our algorithm can also be compared to quasi-Newton methods, but we seek roots rather than stationary points.
no code implementations • 4 Mar 2019 • David Sprunger, Shin-ya Katsumata
When $C$ is equipped with a Cartesian differential operator, we construct a differential operator for $St(C)$ using an abstract version of backpropagation through time, a technique from machine learning based on unrolling of functions.
no code implementations • 25 Mar 2018 • Bart Jacobs, David Sprunger
We illustrate this perspective by training a simple instance of a neural network.