Artificial intelligence · 1949

Hebbian learning

Cells that fire together wire together: the first theory of how networks learn.

Donald Hebb proposed in The Organization of Behavior that a synapse strengthens when the neurons on both sides are active together. It gave neural models a learning rule, and it directly inspired the perceptron, Hopfield networks and unsupervised learning.

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

McCulloch-Pitts neuron 1943

What it led to 2

Perceptron 1958
Hopfield network 1982

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