BraidNet: procedural generation of neural networks for image classification problems using braid theory
Neural and Evolutionary Computing
2021-04-21 v1 Artificial Intelligence
Information Theory
Machine Learning
Geometric Topology
math.IT
Abstract
In this article, we propose the approach to procedural optimization of a neural network, based on the combination of information theory and braid theory. The network studied in the article implemented with the intersections between the braid strands, as well as simplified networks (a network with strands without intersections and a simple convolutional deep neural network), are used to solve various problems of multiclass image classification that allow us to analyze the comparative effectiveness of the proposed architecture. The simulation results showed BraidNet's comparative advantage in learning speed and classification accuracy.
Cite
@article{arxiv.2104.10010,
title = {BraidNet: procedural generation of neural networks for image classification problems using braid theory},
author = {Olga Lukyanova and Oleg Nikitin and Alex Kunin},
journal= {arXiv preprint arXiv:2104.10010},
year = {2021}
}
Comments
9 pages, 8 figures, submitted to the conference ICANN 2021