Artificial intelligence · 1985

Boltzmann machine

A stochastic network that learns hidden features by imitating a probability distribution.

David Ackley, Geoffrey Hinton and Terrence Sejnowski introduced a learning rule for networks with hidden units based on statistical mechanics. Its restricted form powered the deep belief nets that restarted deep learning in 2006.

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 2

Hopfield network 1982
Statistical mechanics 1877

What it led to 1

Deep belief networks 2006

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