The perceptron, developed in the late 1950s by Frank Rosenblatt, is one of the earliest artificial neural networks. It was designed to mimic the way the human brain processes visual information.
Although initially heralded as a breakthrough, its limitations (inability to solve non-linearly separable problems) were later exposed. This led to a period of reduced interest, sometimes called the "AI winter."
Modern developments in multi-layer networks and deep learning have since revolutionized the field, building upon these early ideas.