AI ChronicleAI 纪年 Full timeline →

Research breakthrough · curated entry

Perceptrons maps the limits of single-layer networks

Perceptrons: An Introduction to Computational Geometry

Date
1969
Category
Research breakthrough
Organization / Model
MIT Press
Evidence
1 source · 1 evidence family

Minsky and Papert published Perceptrons, proving rigorously that a single-layer perceptron cannot represent nonlinear functions such as exclusive-or. The book is often read as the turning point that pushed neural-network research into a long slump.

Curator's note: Cross-checked against the MIT Press bibliographic page.

Curated sources · 1

  1. Official announcement · MIT Press1969-01-01

    Perceptrons: An Introduction to Computational Geometry

    mitpress.mit.edu

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. 《Perceptrons》指出单层感知机的表达局限[EB/OL]. (1969)[2026-11-03]. https://aihist.net/e/perceptrons-1969.html.

APA 7 · American Psychological Association

AI 纪年. (1969). 《Perceptrons》指出单层感知机的表达局限 [Web page]. https://aihist.net/e/perceptrons-1969.html

MLA 9 · Modern Language Association

"《Perceptrons》指出单层感知机的表达局限." AI 纪年, 1969, aihist.net/e/perceptrons-1969.html. Accessed 3 Nov. 2026.

Chicago 17 · notes-bibliography

AI 纪年. "《Perceptrons》指出单层感知机的表达局限." Published 1969. Accessed Nov. 3, 2026. https://aihist.net/e/perceptrons-1969.html.

IEEE · citation-reference list

"《Perceptrons》指出单层感知机的表达局限," AI 纪年, 1969. [Online]. Available: https://aihist.net/e/perceptrons-1969.html. [Accessed: 3 Nov. 2026].

ACM · author-date variant

AI 纪年. 1969. 《Perceptrons》指出单层感知机的表达局限. Retrieved November 3, 2026 from https://aihist.net/e/perceptrons-1969.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.