Artificial intelligence · 1998

LeNet-5

A convolutional net reads a large share of US bank checks.

LeCun, Bottou, Bengio and Haffner's LeNet-5 paper set the template of convolution, pooling and fully connected layers. Deployed by NCR, systems built on it read an estimated 10% or more of checks in the US in the late 1990s.

See it in the living tree Wikipedia

Arcs above join it to what it stood on, arcs below to what it led to. The bar places this stretch on the tree's whole timeline.

What it built on 1

Convolutional neural network 1989

What it led to 1

MNIST dataset 1998

Related measurements

The dashed line marks when it first worked.

Training compute of notable AI models Source: Epoch AI, Notable AI Models (CC BY 4.0)

Computation per constant dollar, 1850-2006 Latest: 7.3B million units of computer power per 2006 $ (2003) Source: Nordhaus 2007, Two Centuries of Productivity Growth in Computing, J. Econ. Hist. 67(1), Table 6