korrents

korrents · papers

Gradient-based learning applied to document recognition (with 3 co-authors)

Yoshua Bengio · 1 Jan 1998 · doi.org

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

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.

  1. Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique.
  2. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing.
  3. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques.
  4. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure.