The study of how systems, whether machines, animals, people or organisations, control themselves by sensing what is happening and correcting course. A thermostat is the simplest example: it measures the temperature, compares it with the target and switches the heating on or off. The field shaped early thinking about intelligent machines and made feedback a central idea.
Technical view
Named by Norbert Wiener in his 1948 book Cybernetics: Or Control and Communication in the Animal and the Machine, and developed through the postwar Macy conferences with figures such as Warren McCulloch, whose model of artificial neurons with Walter Pitts fed directly into neural networks. Its core ideas are feedback, homeostasis, information and self-regulation; the British psychiatrist W. Ross Ashby added the law of requisite variety. Overshadowed by symbolic AI from the late 1950s, its concerns resurface in control theory, reinforcement learning and the study of adaptive systems.
Related
Part of AI Terminology Index, section: Adjacent Fields.