OBJECT RECORD / AIM-DOC-1989-001

Backpropagation Applied to Handwritten Zip Code Recognition

A Bell Labs paper records one trainable network reading normalized images of handwritten postal digits.

CURATORIAL READING

Why it is here

LeCun and colleagues describe putting task constraints into the network architecture and training a single network for the whole recognition operation, from a normalized character image to its final classification.

Evidence boundary

The museum checked the abstract, not the full paper. This record supports the stated postal-digit task and image-to-classification path; it does not support calling the system the first convolutional network or a general-purpose vision system.

PROVENANCE

Source trail