[ad_1]
The tabular arrangement of chemical elements, ordered by atomic numbers, electronic configuration and chemical properties – commonly called periodic table – has not only become the preferred poster in classrooms around the world, but also represents a century of point by the most brilliant scientists around the world.
The first version of modern periodic table, which played a role in the prediction of new elements in the universe and their behavior, was proposed by the Russian chemist Dmitri Mendeleev in 1869. But the trip to the periodic table in its current form began in 1789 when Antoine Lavoisier published a list of 33 elements, grouping them in gas, metals, non-metals and land, eventually leading to a century of chemists dedicated to the classification of elements.
This monumental exercise in science has been replicated by an artificial intelligence (AI) program developed by Stanford physicists in a few hours.
The AI program, called Atom2Vec, first learned to distinguish different atoms after analyzing a list of chemical compound names from an online database, Phys reported. Then he used concepts borrowed from the field of natural language processing to group elements according to their chemical properties. From these scattered data, the program understood, for example, that potassium and sodium must have similar properties because both elements can bind to chlorine.
"We wanted to know if an AI could be smart enough to discover the periodic table alone, and our team showed that it could," said study leader Shou-Cheng Zhang. Zhang said that the research was published in the June 25 issue Proceedings of the National Academy of Sciences.
He hopes that in the future, scientists will exploit Atom2Vec's knowledge to design new materials. "For this project, the AI program was not supervised, but you can imagine giving it a goal and asking it to find, for example, a very effective material for converting sunlight into energy "Zhang said.
[ad_2]
Source link
