Hacker News Reader

Comment by grey-area | Hacker News Reader

This is an illuminating definition of deep learning from the end of the article:

The goal of supervised deep learning is to solve almost any problem of the form “map X to Y”. X can include images, speech, or text, and Y can include categories or even sentences.

Interesting to think about the implications when such systems become commonplace.

View on HN

I know what they mean, but you could say the goal of any program is to "map X to Y" where X are the inputs and Y are the desired outputs :)

It's a bit more precise than that because of the examples given, but also the interesting bit is that it does it with only general guidance from the programmer, on a set of x which is not previously known. Up to now algorithms have encoded domain knowledge, but that's about to change if deep learning lives up to its promise.

That's kind of the point. If you can solve the general case, you can solve all the instances too.

One thing I've heard talked about is to use deep learning to re-learn arbitrary programs from their inputs and outputs... Then you can throw away the program and just run the neural network.

I'm sort of a skeptic, so I think that would just make the programs massively less efficient (usually), more incorrect, and harder to maintain, but I guess it's a research direction. Maybe programmers need to be put out of a job :)

> arbitrary programs

It would be really fun to see a web app built on those principles! User clicks on /login/ link -> neural network {"hum ... I wonder what she's after ... let's send her a login form"} -> response.

Trained on millions of MechanicalTurkers ... optimizing the function "which user can you keep engaged the longest". :)

Supervised learning is function approximation given examples of inputs and outputs, plain and simple. So yes, of course a function is anything that maps X to Y. Deep learning just does that with lots of computation steps.

Perhaps only illuminating if you don't know much about the subject already :)

I'm more interested to think about what happens when these structured systems become autonomous from unstructured data.

Can you elaborate, I'm not sure I understand?

Reply on news.ycombinator.com