hep-thNov 16, 2026

Learning from Duality in Neural Network Field Theories

Authors: Pietro Capuozzo, Brandon Robinson, Benjamin Suzzoni

Organizations: STAG Research Centre, University of Southampton, Southampton, SO17 1BJ, UK · Institute of Physics, University of Amsterdam, 904 Science Park, 1098 XH Amsterdam, Netherlands · Department of Mathematical Sciences, Ulsan National Institute of Science and Technology, 50 UNIST-gil, Ulsan 44919, South Korea

Abstract

We develop neural realizations of positive-level Wess-Zumino-Witten models using bosonic Wakimoto and fermionic Fourier-Berezin fields. Level-rank duality connects the charged sectors of the fermionic construction, where explicit neural observables recover conformal block data and enable the transfer of information about unknown correlators between paired theories. We also show that distinct neural presentations of the same continuum current algebra exhibit different finite-width behavior, with approximation accuracy depending on architecture, regulator, and parameter distribution. These results connect the exact mathematical structure of conformal field theory with the expressive and computational properties of neural field theories.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. What Neural Network Field Theory Can and Cannot Realise on a Computer

    Aug 21, 2026Thomas R. HarveyHigh-Energy Physics

  2. Spinning Conformal Correlators from Neural Networks

    Aug 15, 2026Manas Dogra, James Halverson, Joydeep NaskarHigh-Energy Physics

  3. Neural Network Field Theory at Finite Width

    Aug 21, 2026Christian Ferko, Aaron MutchlerFinite-Width Neural Network TheoryHigh-Energy Physics