Wilson, P;
Zanasi, F;
(2022)
Categories of Differentiable Polynomial Circuits for Machine Learning.
In:
International Conference on Graph Transformation.
(pp. pp. 77-93).
Springer Nature
Preview |
Text
Wilson-Zanasi2022_Chapter_CategoriesOfDifferentiablePoly.pdf - Published Version Download (323kB) | Preview |
Abstract
Reverse derivative categories (RDCs) have recently been shown to be a suitable semantic framework for studying machine learning algorithms. Whereas emphasis has been put on training methodologies, less attention has been devoted to particular model classes: the concrete categories whose morphisms represent machine learning models. In this paper we study presentations by generators and equations of classes of RDCs. In particular, we propose polynomial circuits as a suitable machine learning model. We give an axiomatisation for these circuits and prove a functional completeness result. Finally, we discuss the use of polynomial circuits over specific semirings to perform machine learning with discrete values.
| Type: | Proceedings paper |
|---|---|
| Title: | Categories of Differentiable Polynomial Circuits for Machine Learning |
| Event: | ICGT 2022 |
| ISBN-13: | 9783031098420 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/978-3-031-09843-7_5 |
| Publisher version: | https://doi.org/10.1007/978-3-031-09843-7_5 |
| Language: | English |
| Additional information: | © 2022 The Author(s). This work is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/). |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10153644 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
