Research breakthrough · curated entry
AlexNet wins ImageNet and deep learning takes off
ImageNet Classification with Deep Convolutional Neural Networks
- Date
- December 3, 2012
- Category
- Research breakthrough
- Organization / Model
- University of Toronto
- Evidence
- 1 source · 1 evidence family
Krizhevsky, Sutskever and Hinton's AlexNet won the ImageNet challenge by a wide margin, training a deep convolutional network with GPUs, ReLU and dropout. It marked the moment deep learning took over computer vision.
Curator's note: Cross-checked against the NeurIPS paper page.
Curated sources · 1
-
Original paper · NeurIPS 20122012-12-03
ImageNet Classification with Deep Convolutional Neural Networks
papers.nips.cc
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. AlexNet 赢得 ImageNet,深度学习全面爆发[EB/OL]. (2012-12-03)[2026-11-03]. https://aihist.net/e/alexnet-2012.html.
APA 7 · American Psychological Association
AI 纪年. (2012, December 3). AlexNet 赢得 ImageNet,深度学习全面爆发 [Web page]. https://aihist.net/e/alexnet-2012.html
MLA 9 · Modern Language Association
"AlexNet 赢得 ImageNet,深度学习全面爆发." AI 纪年, 3 Dec. 2012, aihist.net/e/alexnet-2012.html. Accessed 3 Nov. 2026.
Chicago 17 · notes-bibliography
AI 纪年. "AlexNet 赢得 ImageNet,深度学习全面爆发." Published Dec. 3, 2012. Accessed Nov. 3, 2026. https://aihist.net/e/alexnet-2012.html.
IEEE · citation-reference list
"AlexNet 赢得 ImageNet,深度学习全面爆发," AI 纪年, 3 Dec. 2012. [Online]. Available: https://aihist.net/e/alexnet-2012.html. [Accessed: 3 Nov. 2026].
ACM · author-date variant
AI 纪年. December 3, 2012. AlexNet 赢得 ImageNet,深度学习全面爆发. Retrieved November 3, 2026 from https://aihist.net/e/alexnet-2012.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.