What is a perceptron, and how does it serve as the building block of AI?
Reviewed by Jason Burns, Editorial Steward · Last updated
A perceptron is the simplest artificial neuron: it takes a weighted sum of its inputs, adds a bias, and passes the result through an activation function to produce an output; it is the historical building block from which modern neural networks are built. As Frank Rosenblatt, put it on the record: "The perceptron is designed to illustrate some of the fundamental properties of intelligent systems in general, without becoming too deeply enmeshed in the special, and frequently unknown, conditions which hold for particular biological organisms."