A computer that learns to play a “scissors, paper, stone” game by observing and mimicking human players could lead to machines that automatically learn how to spot an intruder or perform vital maintenance work, say UK researchers.

In contrast to older AI programs that mimic human behaviour using hard-coded rules, CogVis, developed by scientists at the University of Leeds, learns through observation and mimicry. It teaches itself how to play the children’s game by searching for patterns in video and audio of human players and then building its own “hypotheses” about the game’s rules.