I wish this article was longer. I haven't read the original paper.
A more fruitful approach, and the one employed by scientists, is to create small models or theories that apply to subsets of observational data and then adding these small theories together until you hopefully arrive at a “theory of everything.”
Teaching AI how to partition data to create small models that can be added together to create larger models has proven to be remarkably challenging for machine learning researchers. As detailed in a paper posted to arXiv last week, however, Tailin Wu and Max Tegmark, two physicists from MIT, have made a major step in that direction with their “AI physicist.”
To make this happen, Tegmark and Wu endowed their machine learning algorithm with four strategies that are also employed by human scientists so that it could generate theories about complex observations. These strategies were divide-and-conquer (generate multiple theories, each of which fits only a part of the data), Occam’s razor (use the simplest possible theory), unification (combine the theories) and “lifelong learning” (try applying the theories to future problems).
After these strategies were coded into the machine learning algorithm, Tegmark and Wu presented it with a series of increasingly complex virtual environments governed by strange physical laws and tasked the AI with making sense of it. In particular, the goal of the AI was to predict the motion of an object in two-dimensions as accurately as possible. This would require the AI to generate unique physical theories for each “mystery environment” to understand how an object would move in that environment.
As Tegmark and Wu discovered, the AI physicist has an increasingly hard time understanding the laws of physics as the environments become more complicated. All told, the AI physicist was exposed to 40 different mystery environments and was able to generate correct theories about the physical laws that governed them in over 90 percent of the cases. Moreover, Tegmark and Wu’s AI physicist was able to reduce prediction errors a “billionfold” over conventional machine learning algorithms.
https://motherboard.vice.com/en_us/article/evwj9p/researchers-created-an-ai-physicist-that-can-derive-the-laws-of-physics-in-imaginary-universes
Sister blog of Physicists of the Caribbean in which I babble about non-astronomy stuff, because everyone needs a hobby
Subscribe to:
Post Comments (Atom)
Whose cloud is it anyway ?
I really don't understand the most militant climate activists who are also opposed to geoengineering . Or rather, I think I understand t...
-
"To claim that you are being discriminated against because you have lost your right to discriminate against others shows a gross lack o...
-
For all that I know the Universe is under no obligation to make intuitive sense, I still don't like quantum mechanics. Just because some...
-
Hmmm. [The comments below include a prime example of someone claiming they're interested in truth but just want higher standard, where...
Not to pick nits...well, OK, precisely to pick nits: the "AI" in the picture made a mistake.
ReplyDelete(Missing '3' in one of the cube roots.)
:-)
Greg Roelofs maybe it’s still learning?
ReplyDeleteSure, let's go with that. :-)
ReplyDelete