It’s official. AI is smarter than the human brain and will probably take over the world sooner than we imagined (let’s hope not).
There was a time when scientists took help and guidance from books and journals of previous mathematicians and physicians when they were stuck on a problem. And then used that knowledge to build new software and artificial intelligence. But now it seems like the reverse is happening and scientists are turning to AI for help. How the turntables…
Electric vehicles have taken the world by storm with more and more companies switching to environmentally friendly materials to construct vehicles and reduce carbon emissions. But in this race for EVs, companies are now running out of materials to make the batteries that run the vehicles. When all hope seemed lost, scientists turned to AI in an inevitable twist of fate and relied on machines that they programmed themselves to help them with their own problems.
The researchers from the University of Liverpool in England developed a neural network that ranked different chemical combinations by how likely it was going to result in a useful new material. The rankings were than used to guide their experiments in the laboratory. With the help of AI, they discovered four new useful materials from more than 300 options without having to test everything on the list, saving months of trial and error.
“It’s a great tool,” says Andrij Vasylenko, a research associate at the University of Liverpool and a co-author of the study on finding battery materials, which was published in Nature Communications last month. The A.I. process helps identify the chemical combinations that are worth looking at, he adds, so “we can cover much more chemical space more quickly.”
Humans have created hypotheses for a long time now but using machine learning to produce their own original insights is certainly a new dimension that will quickly gain popularity in modern sciences.