Atlas record: https://www.aitimeline.dev/en/events/evt-0178/
Research · November 1998
LeNet-5 and MNIST
The paper set out a complete convolutional architecture for document recognition and, with it, a handwritten digit set that became a shared ruler.
Why it matters
The architecture and the dataset AlexNet was built on fourteen years later appear here in finished form.
LeNet-5 has seven layers not counting the input (three convolutional, two subsampling, one fully connected and an output layer) and trains end to end by gradient, from pixels to answer. The authors assembled the 70,000-image MNIST set from NIST digit databases: SD-3 was written by Census Bureau employees, SD-1 by high-school students. It is still the most common teaching example. The paper also argues a broader thesis: a document is better recognised by one trained system than by a chain of separately tuned steps.
Event record
- Event date
- November 1998
- Timeline date
- Event date
- Verification
- Sources gathered automatically · September 17, 2026
- Lines
- ID
- evt-0178
Proceedings of the IEEE volume 86, issue 11, November 1998.
Related events
Earlier
- Related A convolutional network reads cheques in banks 1996links to this record
The network reading the cheques is LeNet-5, whose full account appeared the next year.
- Related The Penn Treebank 1993
The same principle: a shared labelled set makes comparison possible.
- Enables NIST's shared test on handwritten characters 1992links to this record
MNIST was built from NIST Special Database 3, the training disc of this conference, and Special Database 1.
- THE MNIST DATABASE of handwritten digits (Yann LeCun, Corinna Cortes) · yann.lecun.com; Wayback Machine capture of 6 February 2005
- The First Census Optical Character Recognition System Conference (R. Allen Wilkinson, Jon Geist, Stanley Janet, Patrick J. Grother, Christopher J. C. Burges, Robert Creecy, Bob Hammond, Jonathan J. Hull, Norman J. Larsen, Thomas P. Vogl, Charles L. Wilson), NISTIR 4912, August 1992 · National Institute of Standards and Technology
- Extends A convolutional network on zip codes 1989
The full account of the architecture shown on zip codes in 1989.
Later