Google Open Sources Its Exoplanet-Hunting AI (vice.com) 16
dmoberhaus writes:
Last December, NASA announced that two new exoplanets had been hiding in plain sight among data from the Kepler space telescope. These two new planets weren't discovered by a human, however. Instead, an exoplanet hunting neural network -- a type of machine learning algorithm loosely modeled after the human brain -- had discovered the planets by finding subtle patterns in the Kepler data that would've been nearly impossible for a human to see. Last Thursday, Christopher Shallue, the lead Google engineer behind the exoplanet AI, announced in a blog post that the company was making the algorithm open source. In other words, anyone can download the code and help hunt for exoplanets in Kepler data.
Google's research blog called the December discovery "a successful proof-of-concept for using machine learning to discover exoplanets, and more generally another example of using machine learning to make meaningful gains in a variety of scientific disciplines (e.g. healthcare, quantum chemistry, and fusion research)."
Google's research blog called the December discovery "a successful proof-of-concept for using machine learning to discover exoplanets, and more generally another example of using machine learning to make meaningful gains in a variety of scientific disciplines (e.g. healthcare, quantum chemistry, and fusion research)."
The Bond villains are so gonna abuse this (Score:5, Funny)
"And now it will be used to hunt the most dangerous prey of all," said a guy somewhere petting a cat.
Blue Remembered Earth (Score:4, Insightful)
IIRC is the name of Alastair Reynolds books telling the story of when an AI Observatory spotted evidence of another AI.
It's a great read!
Now apply it to finding submarines (Score:2)
Re: (Score:2)
I went to where the AI told me the subs were, but it was just two whales humping.
Re: (Score:3)
If you apply it to sonar data, it could probably find "silent" submarines.
Perhaps, but it cuts both ways. Machine learning can indeed find patterns in sonar data to locate subs. But AI also allows autonomous "air-independent" submarines that have no crew and no pressure hull. They are filled with liquid. The electronics are immersed in inert fluorocarbon fluid. This means there is less for the sonar to bounce off, but also means the sub can go much deeper, below the thermocline and below the "deep scattering layer" that is difficult for sonar to penetrate.
Algorithm (Score:2, Troll)
Python (Score:1)
Python is for homos.
Can I name it? (Score:2)
In other words, anyone can download the code and help hunt for exoplanets in Kepler data.
If I find one, can I name it "Planet McPlanetface?"
Maybe I can make some money selling the naming rights? "McDonaldsworld?"