English

Braid-based architecture search

Machine Learning 2022-07-12 v1 Artificial Intelligence Neural and Evolutionary Computing Geometric Topology

Abstract

In this article, we propose the approach to structural optimization of neural networks, based on the braid theory. The paper describes the basics of braid theory as applied to the description of graph structures of neural networks. It is shown how networks of various topologies can be built using braid structures between layers of neural networks. The operation of a neural network based on the braid theory is compared with a homogeneous deep neural network and a network with random intersections between layers that do not correspond to the ordering of the braids. Results are obtained showing the advantage of braid-based networks over comparable architectures in classification problems.

Keywords

Cite

@article{arxiv.2207.04121,
  title  = {Braid-based architecture search},
  author = {Olga Lukyanova and Oleg Nikitin and Alex Kunin},
  journal= {arXiv preprint arXiv:2207.04121},
  year   = {2022}
}

Comments

10 pages, 8 figures, PRICAI-2022 conference. arXiv admin note: substantial text overlap with arXiv:2104.10010