Neural Network Symmetrisation in Concrete Settings
Machine Learning
2024-12-13 v1
Abstract
Cornish (2024) recently gave a general theory of neural network symmetrisation in the abstract context of Markov categories. We give a high-level overview of these results, and their concrete implications for the symmetrisation of deterministic functions and of Markov kernels.
Cite
@article{arxiv.2412.09469,
title = {Neural Network Symmetrisation in Concrete Settings},
author = {Rob Cornish},
journal= {arXiv preprint arXiv:2412.09469},
year = {2024}
}