The perceptron: a machine that learns
Proposed the perceptron, which adjusts its own weights from examples, and built it in hardware as the Mark I.
Why it matters
The first time a machine learned from data, setting off the first wave of excitement about neural networks.
Costs and controversy
In 1969 Minsky and Papert showed a single-layer perceptron cannot even learn XOR, and neural-network research fell into a long winter.
Built on
Led to
Source: doi.org ↗