Facebook has a neural network that can do advanced math

https://www.technologyreview.com/s/614929/facebook-has-a-neural-network-that-can-do-advanced-math/

by lelf • 7 years ago

46 17 7 years ago

technologyreview.com

plutonorm• 7 years ago

Quick, someone stick the navier-stokes equations in.

perl4ever2• 7 years ago

I'd rather see if it can infer anything about the input from a SHA-256 hash.

abc_lisper• 7 years ago

What about the confidence in the result? Math is never done willy nilly, and without the ability to show how it is done, this will go no where. That said, this is a exciting result

colejohnson662• 7 years ago

That reminds me of a joke that goes something like this:

Me: What is 2+2?
AI: It’s 42.
Me: Wrong, it’s 4. What’s 2+3?
AI: It’s 4.

julienreszka• 7 years ago

Can someone explain me the joke

Someone• 7 years ago

In general, differentiating a function is a lot easier than integrating one.

Because functions can be written in multiple ways (simple example: ‘x+1’ vs ‘1+x’. For harder examples, see for example https://en.wikipedia.org/wiki/List_of_trigonometric_identiti...), it may still be difficult to prove that the derivative of a proposed integral of some function f is equal to f, but most of the time, checking a proposed solution to ".

forgotpwd16• 7 years ago

Is there anything machine learning is bad for?

serf• 7 years ago

unique or novel untrained situations.

that said ,we're not great at those, either.

(untrained meaning that the dataset is a poor match with regards to the expected outcome)

savanaly• 7 years ago

Un-differentiable output. Take, for instance, writing a program. Change the input by the smallest possible amount, one character, and generally the output changes by a rather large amount (it could, say, go from working to failing to compile). Rarely would changing one character get us X% closer to a solution, or produce a change in a working solution that is X% faster.

mturmon• 7 years ago

OTOH, the example in the OP has somewhat the flavor of the hard problem you just sketched.

The tree-based (RPN-esque) notation itself gets around much of the "perturbed program fails to compile" problem.

zepto• 7 years ago

employment

siegelzero• 7 years ago

This paper was posted earlier with Anonymous authors: https://news.ycombinator.com/item?id=21084748

shmageggy• 7 years ago

Other neural nets haven’t progressed beyond simple addition and multiplication, but this one calculates integrals and solves differential equations.

And this one can't solve addition or multiplication. Turns out they are different problem spaces that require different approaches.

Havoc• 7 years ago

Headline reminds me of cold war era "the Soviets have a x that can do y"

Facebook has a neural network that can do advanced math

Related Stories