Slashdot Mirror
MIT Finds 'Grand Unified Theory of AI'
aftab14 writes "'What's brilliant about this (approach) is that it allows you to build a cognitive model in a much more straightforward and transparent way than you could do before,' says Nick Chater, a professor of cognitive and decision sciences at University College London. 'You can imagine all the things that a human knows, and trying to list those would just be an endless task, and it might even be an infinite task. But the magic trick is saying, "No, no, just tell me a few things," and then the brain — or in this case the Church system, hopefully somewhat analogous to the way the mind does it — can churn out, using its probabilistic calculation, all the consequences and inferences. And also, when you give the system new information, it can figure out the consequences of that.'"
My broken url should read: http://www.mit.edu/~ndg/papers/churchUAI08_rev2.pdf
Google quick view didn't work for some reason.
"That things over 200 lbs are unlikely to fly. But wait, 747s are heavier than that. Oh, we need to know that animals over 200 lbs rarely have the ability of flight
what? He specifically stated birds. Not Animals, or inanimate objects.
It looks like this system can change as it is used, effectivly creating a 'lifetime' experience.
This is very promising. In fact, it may be the first step in creating primitive house hold AI.
OR robotic systems used in manufacturing able to adjust the process as it goes. Using inputs to determine better ways to do a job.
The Kruger Dunning explains most post on
q.v. Alonzo Church
From the article:
As a research tool, Goodman has developed a computer programming language called Church — after the great American logician Alonzo Church
Your comment fits the criteria of Flamebait and Offtopic, but definitely NOT Funny.
Mostly, he or his university are just really good at overselling. There are dozens of attempts to combine something like probabilistic inference with something more like logical inference, many of which have associated languages, and it's not clear this one solves any of the problems they have any better.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
I looked at the documentation of this "Church Programming language". Scheme and most other Lisp derivatives have been around longer and can do more. This is neither news nor a revolutionary discovery.
I should add that this is interesting research from a legitimate AI researcher, not some kooky fringe AI. I suspect it may have been his PR department more to blame than him, and his actual academic papers make no similarly overblown claims, and provide pretty fair positioning of how his work relates to existing work.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
They have propellers, not wings.
A propeller is a specific type of wing. Wings are airfoils. Propellers are airfoils. Planes have fixed wings. Helicopters have rotatory wings. Both have wings.
FTA: "In the 1950s and 60s, artificial-intelligence researchers saw themselves as trying to uncover the rules of thought. But those rules turned out to be way more complicated than anyone had imagined. Since then, artificial-intelligence (AI) research has come to rely, instead, on probabilities -- statistical patterns that computers can learn from large sets of training data."
From the viewpoint of Jaynes and many Bayesians, probability IS simply the rules of thought.
There are different sizes of infinity, and therefore it is entirely possible for an infinite task to grow into a larger infinite task.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
This is the exact idea I saw in a Masters project at my University that was completed several years ago.
A student created a modified version of Prolog that would work with probabilities. It was very powerful and was used in the military for some expert systems.
This is nothing new. Probabilistic logic has been around for a very long time.
My Master's advisor also created a similar system for Lisp, which is exactly what this is.
The number of integers is infinite, but it is a different infinity than the number of real numbers. The former is considered countable, the latter uncountable.
If you look up the proof of Fermat's Last Theorum, you'll see it was the comparison of the size of two infinite sets that allowed the proof to be completed.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
In an example, we're told the cassowary is a bird. Then we're told it can weigh almost 200 lbs. Okay. Now you're telling me that it might revise its guess as to whether or not it can fly? Come on! Am I the only person that can see that you've just given me an example where the program magically drums up the rule or probability based rule that "if something weighs almost 200 lbs it probably cannot fly"?
For fucks sake, it was just an example of the kind of inferences a logical rule system can make, not a dump of the AI's knowledge and successful inference databases. I mean you might as well complain that the example given was not written in Church and ergo not understandable by the AI whatsoever.
As the article explains, just not explicitly in the context of that example, it devises these rules from being fed information and using the probabilistic approach to figure out patterns and to infer rules, and that it does this better than other
So in the actual version of the Cassowary problem, you would have first fed it a bunch of data about other birds, their flying capabilities, and their weights. The AI would then look at the data, and infer based on the Emu and the Ostrich that heavy birds can't fly and light birds can, unless they're the mascots of open source operating systems (that was a joke). Then you tell it about the cassowary, but not whether or not it can fly, and it infers based on its rules that the cassowary probably can't fly.
In a sense it does "magically drum up the rule". Yes you still have to feed it data, but the point is that you do not have to manually specify every rule, because it can infer the rules from the data, and the create further inferences for those rules, combining the abilities of a rule-based system with the pattern-recognizing power of probabilistic systems.
So the point is it takes less training, and a relatively small amount of explicitly specified rules.
The enemies of Democracy are
yet, there's scant evidence that the universe is finite. Only WMAP quadrupole data... one number... suggests such a thing.