AI provides a big speed up for the Three-body problem

jeffb

jeffb

ACCESS: Top Secret
Joined
7 October 2012
Messages
1,227
Reaction score
1,721
The mind-bending calculations required to predict how three heavenly bodies orbit each other have baffled physicists since the time of Sir Isaac Newton. Now artificial intelligence (A.I.) has shown that it can solve the problem in a fraction of the time required by previous approaches.

Newton was the first to formulate the problem in the 17th century, but finding a simple way to solve it has proved incredibly difficult. The gravitational interactions between three celestial objects like planets, stars and moons result in a chaotic system -- one that is complex and highly sensitive to the starting positions of each body. Current approaches to solving these problems involve using software that can take weeks or even months to complete calculations. So researchers decided to see if a neural network -- a type of pattern recognizing A.I. that loosely mimics how the brain works -- could do better.
 
Looking at the write-up, they've changed their approach from iterative (calculate the shifts over a short period, update positions, repeat until done), to predictive (work out the pattern in the shifts, repeat until done). In effect they're using a completely different mathematical model. That's a fundamental change, and potentially capable of being done in conventional software. IOW it's not clear the magnitude of the improvement is down to the AI so much as the changed mathematical model.

Now if the neural net came up with the new model, then that's AI. But that's not what the article says.
 

Similar threads

Back
Top Bottom