Atomic shapes are so simple that they can't be broken down any further. Mathematicians are trying to turn to artificial intelligence(AI) for help to build a periodic table of these shapes, hoping it will assist in finding yet-unknown atomic shapes.
Tom Coates at Imperial College London and his colleagues are working to classify atomic shapes known as Fano varieties, which are so simple that they can't be broken down into smaller components. Just as chemists arranged elements in the periodic table by their atomic weight and group to reveal new insights, the researchers hope that organizing these atomic shapes by their various properties will help in understanding them.
The team has given each atomic shape a sequence of numbers based on its features such as the number of holes it has or the extent to which it bends around itself. This acts as a bar code(条形码) to identify it. Coates and his colleagues have now created an AI that can predict certain properties of these shapes from their bar code numbers alone, with an accuracy of 98percent.
The team member Alexander Kasprzyk at the University of Nottingham. UK, says that the AI has let the team organize atomic shapes in a way that begins to follow the periodic table, so that when you read from left to right, or up and down, there seem to be general patterns in the geometry(几何) of the shapes.
Graham Nib lo at the University of Southampton, UK, stresses that humans will still need to understand the results provided by AI and create proofs of these ideas. "AI has definitely got unbelievable abilities. But in the same way that telescopes(望远镜) don't put astronomers out of work, AI doesn't put mathematicians out of work," he says. "It just gives us new backing that allows us to explore parts of the mathematical landscape that are out of reach."
The team hopes to improve the model to the point where missing spaces in its periodic table could point to the existence of unknown shapes.
