---
title: "Neural networks and games"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05706v1"
permalink: "https://feed.astralor.com/items/itm_ea7235c5998e47d96370eb83"
published: "2026-11-03T22:34:21.000Z"
score: 54
channel: "ai"
tags: ["RAG","Neural","Hopfield","Nash","More"]
---

# Neural networks and games

## At a glance

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…

## Key points

- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_ea7235c5998e47d96370eb83