Gradient-based learning applied to document recognition (with 3 co-authors)
4 korrents from this paper
In plain words
Neural nets built for how 2D shapes vary beat every other method at reading handwritten digits, and whole multi-part document readers can be trained end to end the same way. Global training helps real handwriting systems, and a cheque reader built this way reaches record accuracy in commercial use on several million cheques a day. It compares methods on a standard digit task and proposes training multi-part systems as one, building on multilayer networks adjusted by sending errors backward through the layers.
Our summary of the paper, not the authors' words — written to be readable without the field's vocabulary, from the stored copy of the paper and nothing else. Drafted with xai:grok-4.5 and checked by a person. The authors' own sentences are the quotes below.
Near this, by wording
- Attention is all you need 2 claims
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 2 claims
- He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv) 2 claims
- Kingma & Ba, "Adam: A Method for Stochastic Optimization" (arXiv) 2 claims
- ImageNet: A large-scale hierarchical image database (with 5 co-authors) 2 claims
Papers whose claims are worded most like this one's, found by the same hourly pass that draws the map. It is a measure of LANGUAGE, not of agreement or of citation: two papers can be near each other here and flatly contradict one another.
Yoshua Bengio did not write this page.
Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.