New Artificial Intelligence System Recreates Periodic Table Within Hours

Posted: Jun 27 2018, 4:02pm CDT | by , Updated: Jul 4 2018, 3:51am CDT, in Latest Science News

 

This story may contain affiliate links.

New Artificial Intelligence System Recreates Periodic Table Within Hours
Credit: Claire Scully

Researchers believe that AI could be used to discover and design new materials

Periodic table provides an extremely useful framework to classify different types of chemical elements and to explain their behavior. It took humans more than hundreds of years to organize and refine this table. But a new artificial intelligence (AI) system did the same job in just a few hours. AI, called Atom2Vec, successfully learned different atoms from an online database on its own and managed to reconstruct the periodic table. This shows how a machine can learn and play a more creative role in research in the future.

“We wanted to know whether an AI can be smart enough to discover the periodic table on its own, and our team showed that it can.” Study leader Shou-Cheng Zhang from Stanford University said.

Artificial intelligence has come a long way over the years. AI programs can infer patterns and rules from a large database and do specialized tasks like recognizing faces, playing games or driving cars. Still, researchers wonder to what extent an AI system can carry out research autonomously. In artificial intelligence (AI), a Turing Test is a way to determine a machine’s intelligence. In order to pass this test, a system must respond to written questions in a way similar to a human, but this is not as easy as it sounds.

"Humans are the product of evolution and our minds are cluttered with all sorts of irrationalities. For an AI to pass the Turing test, it would need to reproduce all of our human irrationalities. That's very difficult to do, and not a particularly good use of programmers' time,” said Zhang.

“We want to see if we can design an AI that can beat humans in discovering a new law of nature. But in order to do that, we first have to test whether our AI can make some of the greatest discoveries already made by humans."

To achieve the secondary goal, researches modeled an AI program based on a parse natural language. The language converts words into numerical codes or vectors and allows the machine to learn atoms without reference to any specific property of materials. From the large, scattered data, the AI program figured out, for example, that potassium (K) and sodium (Na) must have similar properties because both elements can bind with chlorine (Cl). This work could serve as a crucial step toward discovering and design new materials.

Zhang says. "For this project, the AI program was unsupervised, but you could imagine giving it a goal and directing it to find, for example, a material that is highly efficient at converting sunlight to energy.”

Paper: Quan Zhou el al., "Atom2Vec: Learning atoms for materials discovery," PNAS (2018). www.pnas.org/cgi/doi/10.1073/pnas.1801181115

This story may contain affiliate links.

Loading...

Find rare products online! Get the free Tracker App now.


Download the free Tracker app now to get in-stock alerts on Pomsies, Oculus Go, SNES Classic and more.

Latest News

Comments

The Author

<a href="/latest_stories/all/all/47" rel="author">Hira Bashir</a>
The latest discoveries in science are the passion of Hira Bashir (). With years of experience, she is able to spot the most interesting new achievements of scientists around the world and cover them in easy to understand reporting.

 

 

Advertisement

comments powered by Disqus