BraidNet: procedural generation of neural networks for image classification problems using braid theory

TL;DR

BraidNet introduces a novel neural network architecture based on braid theory, combining information theory to enhance image classification performance with faster learning and improved accuracy.

Contribution

This work presents a new neural network design using braid theory for procedural optimization, demonstrating advantages over traditional architectures.

Findings

BraidNet outperforms simplified networks in learning speed.

BraidNet achieves higher classification accuracy.

The approach effectively applies braid intersections in neural network design.

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.