Discrete neural nets and polymorphic learning
Neural and Evolutionary Computing
2023-11-07 v2 Machine Learning
Combinatorics
Rings and Algebras
Abstract
Theorems from universal algebra such as that of Murski\u{i} from the 1970s have a striking similarity to universal approximation results for neural nets along the lines of Cybenko's from the 1980s. We consider here a discrete analogue of the classical notion of a neural net which places these results in a unified setting. We introduce a learning algorithm based on polymorphisms of relational structures and show how to use it for a classical learning task.
Cite
@article{arxiv.2308.00677,
title = {Discrete neural nets and polymorphic learning},
author = {Charlotte Aten},
journal= {arXiv preprint arXiv:2308.00677},
year = {2023}
}
Comments
Version 2 includes the figures which were missing in the first version