Slide: 1 \/ of 1. Caption: Brad Goldpaint\/Getty Images <\/p>\n
Astronomer Kevin Schawinski has spent much of his career studying how massive black holes shape galaxies. But he isnt into dirty workdealing with messy dataso he decided to figure out how neural networks could do it for him. Problem is, he and his cosmic colleagues suck at that sophisticated kind of coding. <\/p>\n
That changed when another professor at Schawinskis institution, ETH Zurich, sent him an email and CCed Ce Zhang, who actually is a computer scientist. You guys should talk, the email said. And they did: Together, they plotted how they could take leading-edge machine-learning techniques and superimpose them on the universe. And recently, they released their first result: a neural network that sharpens up blurry, noisy images from space. Kind of like those scenes in CSI-type shows where a character shouts Enhance! Enhance! at gas station security footage, and all of a sudden the perps face resolves before your eyes. <\/p>\n
Schawinski and Zhangs work is part of a larger automation trend in astronomy: Autodidactic machines can identify, classify, andapparentlyclean up their data better and faster than any humans. And soon, machine learning will be a standard digital tool astronomers can pull out, without even needing to grasp the backend. <\/p>\n
In their initial research, Schawinski and Zhang came across a kind of neural net that, in an example, generated original pictures of cats after learning what cat-ness is from a set of feline images. It immediately became clear, says Schawinski. <\/p>\n
This feline-friendly system was called a GAN, or generative adversarial network. It pits two machine-brainseach its own neural networkagainst each other. To train the system, they gave one of the brains a purposefully noisy, blurry image of a cat galaxy and then an unmarred version of that same galaxy. That network did its best to fix the degraded galaxy, making it match the pristine one. The second half of the network evaluated the differences between that fixed image and the originally OK one. In test mode, the GAN got a new set of scarred pictures and performed computational plastic surgery. <\/p>\n
Once trained up, the GAN revealed details that telescopes werent sensitive enough to resolve, like star-forming spots. I dont want to use a clich phrase like holy grail, says Schawinski, but in astronomy, you really want to take an image and make it better than it actually is. <\/p>\n
When I asked the two scientists, who Skyped me together on Friday, whats next for their silicon brains, Schawinski asked Zhang, How much can we reveal? which suggests to me they plan to take over the world. <\/p>\n
They went on to say, though, that they dont exactly know, short-term (or at least theyre not telling). Long-term, these machine learning techniques just become part of the arsenal scientists use, says Schawinski, in a kind of ready-to-eat form. Scientists shouldnt have to be experts on deep learning and have all the arcane knowledge that only five people in the world can grapple with. <\/p>\n
Other astronomers have already used machine learning to do some of their work. A set of scientists at ETH Zurich, for example, used artificial intelligence to combat contamination in radio data. They trained a neural network to recognize and then mask the human-made radio interference that comes from satellites, airports, WiFi routers, microwaves, and malfunctioning electric blankets. Which is good, because the number of electronic devices will only increase, while black holes arent getting any brighter. <\/p>\n
Neural networks need not limit themselves to new astronomical observations, though. Scientists have been dragging digital data from the sky for decades, and they can improve those old observations by plugging them into new pipelines. With the same data people had before, we can learn more about the universe, says Schawinski. <\/p>\n
Machine learning also makes data less tedious to process. Much of astronomers work once involved the slog of searching for the same kinds of signals over and overthe blips of pulsars, the arms of galaxies, the spectra of star-forming regionsand figuring out how to automate that slogging. But when a machine learns, it figures out how to automate the slogging. The code itself decides that galaxy type 16 exists and has spiral arms and then says, Found another one! As Alex Hocking, who developed one such system, put it, the important thing about our algorithm is that we have not told the machine what to look for in the images, but instead taught it how to see. <\/p>\n
A prototype neural network that pulsar astronomers developed in 2012 found 85 percent of the pulsars in a test dataset; a 2016 system flags fast radio burst candidates as human- or space-made, and from a known source or from a mystery object. On the optical side, a computer brainweb called RobERtRobotic Exoplanet Recognitionprocesses the chemical fingerprints in planetary systems, doing in seconds what once took scientists days or weeks. Even creepier, when the astronomers asked RobERt to dream up what water would look like, he, uh, did it. <\/p>\n
The point, here, is that computers are better and faster at some parts of astronomy than astronomers are. And they will continue to change science, freeing up scientists time and wetware for more interesting problems than whether a signal is spurious or a galaxy is elliptical. Artificial intelligence has broken into scientific research in a big way, says Schawinski. This is a beginning of an explosion. This is what excites me the most about this moment. We are witnessing anda little bitshaping the way were going to do scientific work in the future. <\/p>\n
<\/p>\n
Continued here: <\/p>\n
Astronomers Deploy AI to Unravel the Mysteries of the Universe - WIRED<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Slide: 1 \/ of 1. Caption: Brad Goldpaint\/Getty Images Astronomer Kevin Schawinski has spent much of his career studying how massive black holes shape galaxies. But he isnt into dirty workdealing with messy dataso he decided to figure out how neural networks could do it for him. Continue reading