cs.NENov 3, 2026

Neural networks and games

Authors: Philip R. Neary

Organizations: Economics Department, Royal Holloway University of London

Abstract

Hopfield neural networks and noncooperative games provide seemingly different approaches to understanding how collective outcomes emerge from local interactions. In a neural network, individual units adjust their states according to local signals; in a game, players choose actions to maximise individual payoffs. I establish an exact equivalence between symmetric binary Hopfield networks and binary-action games that admit a quadratic potential. The equivalence identifies stable network configurations with pure-strategy Nash equilibria, and asynchronous neural updating with best-response dynamics. More broadly, the storage and retrieval of memories in neural networks correspond, respectively, to the design and selection of equilibria in games.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DiffNash: Finding Nash Equilibrium in High-Dimensional Continuous Action Spaces with Diffusion Policies

    Oct 11, 2026Haichuan Wang, Anagha Satish, Jiale Zheng +4Nash Equilibrium ComputationGame-Playing Agents

  2. Overcoming a Learning Bottleneck in Impartial Games: A Circuit Complexity Approach

    Nov 10, 2024Søren RiisCircuit ComplexityNeural Network Expressivity

  3. A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics

    Apr 30, 2026Djamel Bouchaffra, Faycal Ykhlef, Mustapha Lebbah +1Nash EquilibriumCooperative Game Theory