Did you know that the same class of algorithms is being used by Google, Netflix, and for exploring distant planetary systems? From fraud detection in Google and making movie recommendations on Netflix, to detecting exoplanets and telling whether or not distant planetary systems are stable, today’s algorithms seem capable of everything.
Machine learning algorithms, being a part of artificial intelligence, have the ability to learn without having to be constantly programmed for specific tasks. This makes them extremely powerful in tackling problems in astrophysics for example.
Now a team of researchers from the University of Toronto Scarborough has developed a new approach in using it to determine whether planetary systems are stable or not. Their method is 1,000 times faster than any traditional method in predicting stability.
Dan Tamayo, who is a postdoctoral fellow in the Centre for Planetary Science at U of T Scarborough, and who led this research said: “In the past we’ve been hamstrung in trying to figure out whether planetary systems are stable by methods that couldn’t handle the amount of data we were throwing at it.”
The reason why knowing whether planetary systems are stable or not is important is because this information can tell us a lot about how planetary systems are formed. We also get valuable new information about exoplanets that is not offered by current methods of observation.
Source:
University of Toronto (http://ose.utsc.utoronto.ca/ose/story.php?id=9036)
The Wonderful World of Algorithms 