Researchers have developed an artificial intelligence capable of recreating the physics experiment that won the 2001 Nobel Prize.
The AI system was able to recreate the complex quantum experiment to create an extremely cold gas trapped in a laser beam, known as a Bose-Einstein condensate.
“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, of the Australian National University Research School of Physics and Engineering, in a statement.
“A simple computer program would have taken longer than the age of the universe to run through all the combinations and work this out.”
Wigley, along with colleagues from the University of Adelaide and the University of South Wales Australian Defence Force Academy (UNSW ADFA), developed the online optimisation process based on machine learning to help find the best way to produce Bose-Einstein condensates (BEC).
The physicists made the ultra-cold gas, which is “less than a billionth of a degree above absolute zero”, and let the AI take over from there.
Scientists want to be able to create BECs to use them as cold-atom based sensors and to investigate many-body physics, among other uses. Because they are super-sensitive to external disturbances, they can take very precise measurements of things like tiny changes in the Earth’s magnetic field or gravity.
With the AI, a BEC system could be set up quickly each morning and the machine would compensate for any overnight fluctuations, allowing it to be taken out into the field.
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 from UNSW ADFA.
“It’s cheaper than taking a physicist everywhere with you.”
The researchers also found that the AI came up with ways to make the BEC that surprised them.
“It did things a person wouldn’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.”
The team has made their machine learning online optimisation algorithm available online and believe it could be applied to experiments in quantum chemistry, femtosecond physics and quantum computing.
They intend to continue to the BEC experiments with the AI.
“Next we plan to employ the artificial intelligence to build an even larger Bose-Einstein condensate faster than we’ve seen ever before,” Hush said.
The research is available online in Nature’s Scientific Reports.