LeCun, Bottou, Bengio and Haffner: gradient-based document recognition and LeNet-5

What changed

Convolutional vision and task-level optimization formed a concrete document-recognition system.

Scientific scope

1998 four-author paper and reported systems; not first CNN, all deep learning or later models.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact four-author 1998 paper and the systems it reports. It is not a claim of the first convolutional network, sole credit for deep learning, or ownership of later CNN architectures and applications.

Contributors

• Yann LeCun · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Léon Bottou · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Yoshua Bengio · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Patrick Haffner · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Crossref record for Gradient-based learning applied to document recognition
• LeCun et al., Gradient-Based Learning Applied to Document Recognition

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction