On Wednesday, scientists said that an Artificial Intelligence(AI) program used to recognize faces on Facebook can also be used to identify galaxies in deep space.
The name of this AI bot is ClaRAN. It scans the images taken by ratio telescope, said by the researchers from the International Center for Radio Astronomy Research (ICRAR) in Australia.
ClaRAN uses is to spot radio galaxy-galaxies that throw powerful radio jets from supermassive black hole at their center. It published by researchers in the Journal Monthly Notice of the Royal Astronomical Society.
Black holes are seen in the center of the most, if not all galaxies.
“This supermassive black holes occasionally burp out jets that can be seen with a radio telescope” said by Ivy Wong from The University Of Western Australia of International Center for Radio Astronomy Research (ICRAR).
“Over time, the jet can stretch a long way from their host galaxies, making it difficult for traditional computer programs to figure out where the galaxy is,” also added by Ivy Wong.
She added that the upcoming EMU survey using the Australian Square Kilometer Array Pathfinder (ASKAP) telescope is assumed to see up to 70 million galaxy across the history of the universe.
Wong said that the program was completely refurbished and trained to recognize the galaxy instead of people.
The AI bot ClaRAN grew out of an open source of Facebook and Microsoft ‘s object detection software.
Ivy said that traditional computer algorithms are able to correctly recognize 90% of the source.
“That still leaves 10%, or seven million ‘difficult’ galaxies that have to be eyeballed by a human due to the complexity of their extended structure” said by Wang.
She said,”If ClaRAN reduces the number of sources that require visual classification down to 1%, this mean more time for our citizen scientists to spend looked at new types of galaxies,”
Radio Galaxy Zoo volunteers was produced a highly-accurate catalog that was used to train ClaRAN how to spot where the jets originate.
ClaRAN is an example of a new paradigm called ‘programming 2.0’ said by Chen Wu, also a member from ICRAR.
“All you do is set up a huge neural network, give it a tonne of data, and let it figure out how to adject its natural connections in order to generate the expected outcome” said Chen Wu.
Do you like it? Don’t forget to share it.