AI ChronicleAI 纪年 Full timeline →

Research breakthrough · curated entry

Hopfield gives neural networks an energy function

Neural networks and physical systems with emergent collective computational abilities

Date
April 1982
Category
Research breakthrough
Organization / Model
Caltech
Evidence
1 source · 1 evidence family

He mapped symmetrically connected recurrent networks onto spin-glass models, using an energy function to explain how a network settles into stable states and performs associative memory. It brought neural networks back into the shared view of physics and engineering, preparing the connectionist revival of the 1980s.

Curator's note: Cross-checked against the PNAS paper DOI; the 2024 Nobel Prize in Physics recognized this work.

Curated sources · 1

  1. Original paper · PNAS1982-04-01

    Neural networks and physical systems with emergent collective computational abilities

    doi.org

Cite this page

This page is a curated static snapshot and can be cited directly. Preferred format GB/T 7714—2025 (electronic resource [EB/OL]); the other 5 styles open below, together with the machine-readable files.

GB/T 7714—2025 (electronic resource [EB/OL])

AI 纪年. Hopfield 用能量函数描述神经网络,连接主义重新获得物理基础[EB/OL]. (1982-04)[2026-11-03]. https://aihist.net/e/hopfield-1982.html.

APA 7 · American Psychological Association

AI 纪年. (1982, April). Hopfield 用能量函数描述神经网络,连接主义重新获得物理基础 [Web page]. https://aihist.net/e/hopfield-1982.html

MLA 9 · Modern Language Association

"Hopfield 用能量函数描述神经网络,连接主义重新获得物理基础." AI 纪年, April 1982, aihist.net/e/hopfield-1982.html. Accessed 3 Nov. 2026.

Chicago 17 · notes-bibliography

AI 纪年. "Hopfield 用能量函数描述神经网络,连接主义重新获得物理基础." Published April 1982. Accessed Nov. 3, 2026. https://aihist.net/e/hopfield-1982.html.

IEEE · citation-reference list

"Hopfield 用能量函数描述神经网络,连接主义重新获得物理基础," AI 纪年, Apr. 1982. [Online]. Available: https://aihist.net/e/hopfield-1982.html. [Accessed: 3 Nov. 2026].

ACM · author-date variant

AI 纪年. April 1982. Hopfield 用能量函数描述神经网络,连接主义重新获得物理基础. Retrieved November 3, 2026 from https://aihist.net/e/hopfield-1982.html.

All six styles come from one template and can be compared word for word. [引用日期], Accessed, urldate and Y2 all carry this page's build date, 2026-11-03 — a static page is an immutable snapshot, so substitute the date you actually consulted it. The address in every style is the archive's canonical page: this English page translates the same snapshot, and the work keeps its name, so one record cites both. For one-click copying use the same entry in the timeline, which takes the day you opened it. Expand the other styles before printing.