RGP Neural Architectures
Abstract
A framework implementing the theoretical correspondence between renormalization-group transformations and deep neural network depth. Provides tools for Fisher information geometry, Jacobian spectral analysis, Lyapunov exponent computation, and finite-size scaling validation.
Fields of Study & Subjects
Neural Networks and Applications
Theoretical and Computational Physics
Model Reduction and Neural Networks
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 1 March 2026
- Language
- EN