{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/1989-12-01-lecun-convolutional-networks/","md":"https://postcutoff.com/e/1989-12-01-lecun-convolutional-networks/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"1989-12-01-lecun-convolutional-networks","date":"1989-12-01","date_precision":"year","short_title":"LeCun applies backprop-trained convolutional nets to handwritten digits","deck":null,"takeaway":"Yann LeCun and colleagues trained a convolutional neural network with backpropagation to read handwritten ZIP codes, the lineage that became LeNet-5 and was deployed to read cheques.","category":"research","category_label":"Research","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Backpropagation Applied to Handwritten Zip Code Recognition (DOI)","url":"https://doi.org/10.1162/neco.1989.1.4.541","type":"paper","group":"primary","domain":"doi.org"},{"n":2,"title":"Gradient-based learning applied to document recognition (1998, DOI)","url":"https://doi.org/10.1109/5.726791","type":"paper","group":"primary","domain":"doi.org"},{"n":3,"title":"Wikipedia: LeNet","url":"https://en.wikipedia.org/wiki/LeNet","type":"discussion","group":"reactions","domain":"en.wikipedia.org"}],"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["AT&T Bell Labs"],"title":"LeCun applies backprop-trained convolutional nets to handwritten digits (LeNet)","summary":"Yann LeCun and colleagues trained a convolutional neural network with backpropagation to read handwritten ZIP codes, the lineage that became LeNet-5 and was deployed to read cheques.","key_facts":["Paper: 'Backpropagation Applied to Handwritten Zip Code Recognition', Neural Computation 1(4), 1989","Used weight sharing and local receptive fields (convolutions)","LeNet-5 described in 'Gradient-based learning applied to document recognition' (Proc. IEEE, 1998)","Introduced the MNIST dataset lineage used for decades"],"key_numbers":[],"tags":["computer-vision","cnn","neural-networks"],"science":null,"body_md":"## What happened\n\nAt Bell Labs, LeCun built convolutional networks trained end-to-end with backprop for digit recognition; later versions were used commercially to process a significant share of US cheques.\n\n## Why it matters\n\nConvolutional networks became the backbone of computer vision and the architecture that triggered the deep learning revolution in 2012.","disputed":[],"related":[{"id":"2012-09-30-alexnet","url":"https://postcutoff.com/e/2012-09-30-alexnet/","date":"2012-09-30","date_precision":"day","short_title":"AlexNet wins ImageNet challenge, igniting the deep learning boom","deck":null,"takeaway":"The single event most often cited as the start of the modern AI era: it established GPUs + big data + deep nets as the winning recipe and made NVIDIA central to AI.","category":"research","category_label":"Research","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["University of Toronto"]},{"id":"1986-10-09-backpropagation","url":"https://postcutoff.com/e/1986-10-09-backpropagation/","date":"1986-10-09","date_precision":"day","short_title":"Rumelhart, Hinton & Williams popularize backpropagation","deck":null,"takeaway":"Backpropagation is still how essentially all neural networks, including today's LLMs, are trained.","category":"research","category_label":"Research","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["UC San Diego","Carnegie Mellon University"]}],"people":[{"id":"yann-lecun","name":"Yann LeCun","url":"https://postcutoff.com/person/yann-lecun/"}],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":"https://postcutoff.com/s/lecun-applies-backprop-trained"}