Artificial intelligence · 1960

ADALINE

Widrow and Hoff train a neuron by gradient descent on squared error.

Bernard Widrow and Ted Hoff's ADALINE used the least mean squares rule, adjusting weights in proportion to the continuous error. That gradient-based idea became the core of backpropagation, and LMS adaptive filters still run in modems and echo cancellers.

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

Perceptron 1958

What it led to 1

Backpropagation 1986

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