British researchers have discovered that it is now possible for machines to learn how natural or artificial systems work by simply observing them, without being told what to look for.
The discovery, by researchers at the University of Sheffield, is inspired by the work of computer scientist Alan Turing, who proposed a test which a machine could pass if it behaved indistinguishably from a human.
In the test, an interrogator exchanges messages with two players in a different room: one human, the other a machine.
The interrogator has to find out which of the two players is human. If they consistently fail to do so – meaning that they are no more successful than if they had chosen one player at random – the machine has passed the test, and is considered to have human-level intelligence.
Dr Roderich Gross from the Department of Automatic Control and Systems Engineering and Sheffield Robotics at the University of Sheffield said, “Our study uses the Turing test to reveal how a given system, not necessarily a human, works”.
“We put a swarm of robots under surveillance and wanted to find out which rules caused their movements. To do so, we put a second swarm – made of learning robots – under surveillance too. The movements of all the robots were recorded and the motion data shown to interrogators.
“Unlike in the original Turing test, however, our interrogators are not human but rather computer programs that learn by themselves.
Their task is to distinguish between robots from either swarm. They are rewarded for correctly categorising the motion data from the original swarm as genuine, and those from the other swarm as counterfeit.
The learning robots that succeed in fooling an interrogator – making it believe their motion data were genuine – receive a reward,” he said.
The advantage of the approach — Turing Learning — is that humans no longer need to tell machines what to look for, according to Gross.
“Imagine you want a robot to paint like Picasso. Conventional machine learning algorithms would rate the robot’s paintings for how closely they resembled a Picasso. But someone would have to tell the algorithms what is considered similar to a Picasso to begin with.
“Turing Learning does not require such prior knowledge. It would simply reward the robot if it painted something that was considered genuine by the interrogators.
Turing Learning would simultaneously learn how to interrogate and how to paint. Our interrogators are not human but rather computer programs that learn by themselves. The learning robots that succeed in fooling an interrogator receive a reward,” he said.
“Scientists could use it to discover the rules governing natural or artificial systems, especially where behaviour cannot be easily characterised using similarity metrics,” Gross said, adding that ‘Turing Learning’ could lead to advances in science and technology.
The discovery was published in the journal Swarm Intelligence.