SOURCE-LINKED INTELLIGENCE

Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural Networks

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Artificial neural networks are often regarded as powerful yet opaque black boxes. Here, we demonstrate that learning in deep neural networks generates local symmetries known in graph theory as fibrations and coverings. We prove that covering symmetries are stable attractors of stochastic gradient descent. Consistent with this theory, we report the emergence of covering symmetries across major network architectures, including multilayer, convolutional, recurrent, and transformer networks. Exploiting these symmetries enables drastic model compression - reducing networks to 17% of their original

Read original source ↗ Open in workspace

recordType

paper

region

Global