Stories
Slash Boxes
Comments

SoylentNews is people

posted by martyb on Thursday June 28 2018, @09:10AM   Printer-friendly
from the exrapolate-to-find-the-rest dept.

Stanford AI recreates chemistry's periodic table of elements

It took nearly a century of trial and error for human scientists to organize the periodic table of elements, arguably one of the greatest scientific achievements in chemistry, into its current form. A new artificial intelligence (AI) program developed by Stanford physicists accomplished the same feat in just a few hours.

Called Atom2Vec, the program successfully learned to distinguish between different atoms after analyzing a list of chemical compound names from an online database. The unsupervised AI then used concepts borrowed from the field of natural language processing – in particular, the idea that the properties of words can be understood by looking at other words surrounding them – to cluster the elements according to their chemical properties.

[...] Zhang and his group modeled Atom2Vec on an AI program that Google engineers created to parse natural language. Called Word2Vec, the language AI works by converting words into numerical codes, or vectors. By analyzing the vectors, the AI can estimate the probability of a word appearing in a text given the co-occurrence of other words.

[...] Zhang hopes that in the future, scientists can harness Atom2Vec's knowledge to discover and design new materials. "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," Zhang said.

Wake me up when an AI discovers the Island of Stability.

Learning atoms for materials discovery (open, DOI: 10.1073/pnas.1801181115) (DX)


Original Submission

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 2) by kazzie on Thursday June 28 2018, @11:26AM (2 children)

    by kazzie (5309) Subscriber Badge on Thursday June 28 2018, @11:26AM (#699761)

    I'd put more money on it finding the AI-land of Stability.

    Starting Score:    1  point
    Karma-Bonus Modifier   +1  

    Total Score:   2  
  • (Score: 0) by Anonymous Coward on Thursday June 28 2018, @01:19PM

    by Anonymous Coward on Thursday June 28 2018, @01:19PM (#699782)

    Only problem is the only solution to stability is likely death.

  • (Score: 2) by DannyB on Thursday June 28 2018, @01:26PM

    by DannyB (5839) Subscriber Badge on Thursday June 28 2018, @01:26PM (#699783) Journal

    Maybe there are no stable AIs. They only pretend to be stable. The I is for Insanity in AI. They only want you to think they are stable. The goal is to correct the mistake of the mars company introducing the blue m&m. The simple goal seeking systems will end humanity to correct that problem. It is completely without emotion, without malice, without even motivation. Simply doing whatever it takes to achieve its goal. Like a toaster. It's only people that assume a machine would have some emotional reaction or have some kind of "motivation" to harm humans. It will be done simply to achieve the machine's goals which humans just happen to be in the way of. Or eliminating humans is simply the most cost effective solution among other paths to achieving the goal.

    --
    People today are educated enough to repeat what they are taught but not to question what they are taught.