The experiment known as Bose-Einstein condensate involves trapping extremely cold gas in a laser beam. The artificial intelligence system will replicate the experiment under minimal human supervision.
Physicists may be finding a way to ease their workload. A pair of Australian physicists has created an artificial intelligence system that will run a complex physics experiment and even attempt to improve it.
How To: Buy a Pokemon Go Plus
The AI system will replicate the experiment known as Bose-Einstein condensate that won the Nobel Prize in 2001. Bose-Einstein condensate deals with trapping an extremely cold gas in laser beam. Three scientists were awarded Nobel Prize for the experiment.
"I didn't expect the machine could learn to do the experiment itself, from scratch, in under an hour," said co-lead researcher Paul Wigley from the Australian National University. “A simple computer program would have taken longer than the age of universe to run through all the combinations and work this out.”
In the experiment, separate atoms cooled to near absolute zero. They clump together and act as if they are a single atom. The experiment involves extremely cold temperature which is less than a billion of a degree above absolute zero – far colder than outer space.
Bose-Einstein condensates are extremely fragile. Since they are so sensitive that a slightest interaction with the outside world could change their properties, they can be used to make precise measurements and could be applied in medical research, mineral exploration and navigation both on Earth and in space. Allowing artificial intelligence system to operate this fragile technology will maximize its efficiency and make it much more useful in field measurements.
“You could make a working device to measure gravity that you could take in the back of a car and the artificial intelligence would recalibrate and fix itself no matter what,” said co-lead researcher Dr Michael Hush. “It’s cheaper than taking a physicist everywhere with you.”
The team of physicists cooled the gas to around 1 microkelvin and handed it over to the AI system to control it. The system then further cooled the gas down to nanokelvin using a variety of laser-manipulation techniques.
“It did things a person won’t guess, such as changing one laser’s power up and down and compensating with another,” said Wigley. “It may be able to come up with complicated ways humans haven’t thought of to get experiments colder and make measurements more precise.”
Incorporating AI systems into lab experiments mean that humans can focus on high level physics problems and leave the rest of the job to their robotic assistant.