Post-Cutoff.com
  1. Home
  2. Timeline
  3. 1958
  4. Frank Rosenblatt's Perceptron — the first trainable neural…

Frank Rosenblatt's Perceptron — the first trainable neural network

★★★★★researchCornell Aeronautical LaboratoryUS Office of Naval Researchconfidence: medium

Frank Rosenblatt introduced the perceptron, a neural network that learns its weights from examples, and demonstrated it publicly in 1958; the Mark I Perceptron hardware followed.

Key facts

What happened

Rosenblatt's perceptron learned to classify simple visual patterns by adjusting connection weights, first simulated on an IBM 704 and later built as dedicated hardware.

Why it matters

It was the first learning neural network and the direct ancestor of modern deep learning; the hype and later backlash around it foreshadowed later AI boom-bust cycles.

Changelog

  • 2026-09-29: created

Related events

  1. McCulloch & Pitts publish the first mathematical model of a neural network ★★★★★
  2. Rumelhart, Hinton & Williams popularize backpropagation ★★★★★

Sources (2)

id: 1958-07-01-perceptron · updated 2026-09-29 · open in the interactive timeline