Gradient-based learning applied to document recognition

E74104

research article scientific paper

"Gradient-based learning applied to document recognition" is a seminal 1998 paper by Yann LeCun and colleagues that introduced and demonstrated the effectiveness of convolutional neural networks for tasks like handwritten digit recognition, helping to lay the foundations of modern deep learning.

Jump to: Statements Referenced by

Statements (47)

Predicate	Object
instanceOf	research article ⓘ scientific paper ⓘ
affiliatedInstitution	Bell Telephone Laboratories ⓘ surface form: AT&T Bell Laboratories Université de Montréal ⓘ
applicationDomain	document recognition ⓘ handwritten digit recognition ⓘ
architectureName	LeNet ⓘ
author	Léon Bottou ⓘ Patrick Haffner ⓘ Yann LeCun ⓘ Yoshua Bengio ⓘ
contribution	demonstrated effectiveness of convolutional neural networks for document recognition ⓘ helped establish convolutional neural networks as a standard approach for image recognition tasks ⓘ showed that gradient-based learning can outperform hand-engineered feature systems for character recognition ⓘ
countryOfOrigin	United States of America ⓘ surface form: United States
datasetUsed	MNIST ⓘ
demonstratedOn	bank check recognition ⓘ handwritten ZIP code recognition ⓘ
field	computer vision ⓘ deep learning ⓘ machine learning ⓘ pattern recognition ⓘ
impact	foundational work for modern deep learning ⓘ widely cited in the deep learning literature ⓘ
influenced	applications of deep learning to large-scale image recognition ⓘ development of modern convolutional neural network architectures ⓘ
issue	11 ⓘ
language	English ⓘ
learningAlgorithm	backpropagation of gradients ⓘ stochastic gradient descent ⓘ
mainConcept	backpropagation ⓘ gradient-based learning ⓘ
mainMethod	convolutional neural networks ⓘ
pages	2278–2324 ⓘ
problemAddressed	automatic recognition of handwritten characters ⓘ robust document image understanding ⓘ
publicationYear	1998 ⓘ
publisher	Proceedings of the IEEE ⓘ
shows	hierarchical feature extraction with convolutional layers ⓘ superiority of learned features over handcrafted features for digit recognition ⓘ
technique	end-to-end training ⓘ multi-layer convolutional networks ⓘ shared weights ⓘ subsampling layers ⓘ
timePeriod	late 1990s ⓘ
title	Gradient-based learning applied to document recognition self-link ⓘ
volume	86 ⓘ

Referenced by (3)

Full triples — surface form annotated when it differs from this entity's canonical label.

MNIST → introducedInPublication → Gradient-based learning applied to document recognition ⓘ

LeNet → notablePublication → Gradient-based learning applied to document recognition ⓘ

Gradient-based learning applied to document recognition → title → Gradient-based learning applied to document recognition self-link ⓘ