Braid-based architecture search
This work addresses the challenge of optimizing neural network architectures for researchers in machine learning, though it appears incremental as it builds on existing methods with a novel theoretical twist.
The authors tackled the problem of neural network structural optimization by applying braid theory to design network topologies, showing that braid-based networks outperform comparable architectures in classification tasks.
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.