Back to section
Event · 1958-11

Machine perception

The perceptron

Rosenblatt demonstrated a system that adjusted its weights from examples and learned simple classifications.

The perceptron added the key practical property to the formal neuron: learning from data. Its algorithm corrected weights after an error and gradually built a linear boundary between classes. Its capabilities were limited, but the modern loop of data, error and parameter update begins here.

Sources
Psychological ReviewOpen primary source