How Neural Networks Learn

Turing asked if machines could think. Rosenblatt built one that could learn. The Perceptron is the grandfather of every neural network alive today — the first machine that adjusted itself based on experience, rather than following rules someone wrote by hand.

The Perceptron could learn, but only simple patterns. Multi-layer networks could learn complex patterns, but nobody knew how to train them. This paper answered that question — with a single elegant algorithm that is still the beating heart of every neural network trained today.