WRSWorld Research StateContribute
WORLD RESEARCH STATE

LeCun and colleagues: backpropagation for handwritten zip-code recognition

Contribution grade

Computer vision and neural networks · Empirical recognition systems

Reference score120,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

A structured backpropagation network demonstrated practical handwritten digit recognition.

Scientific scope

The seven-author 1989 paper and its task; not invention of all convolutional networks or later ImageNet-era systems.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. This record is limited to the 1989 seven-author paper and its USPS task; it does not collapse earlier convolutional ideas or later large-scale CNN systems into this work.

Contributors

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