News for hackers. Stuff that matters.
Re:The truth about deep learning by yzmtf2008 on Wednesday June 01, 2016 @10:06PM (#11819866)
The issue here isn't whether there is something deep learning can't learn -- with enough data and engineering even nearest neighbor can learn everything.

The problem is, would deep learning scale efficiently that it is feasible to learn the "universal algorithm" with DL?

Re:The truth about deep learning by eva1984 on Wednesday June 01, 2016 @10:10PM (#11819884)
I think neural nets are approved that with more than 2 hidden layers, it can approximate any functuons. Is there any literature for other algorithms as well?
Re:The truth about deep learning by yzmtf2008 on Wednesday June 01, 2016 @10:18PM (#11819911)
It is true that neural networks can approximate any function. But what are feasible ways to construct such networks? Part of the point of having "deep" networks is that it's easier to train that way. Scalability does not only refer to the scale of the model itself, but also the difficulty in building such model.
Re:The truth about deep learning by return0 on Wednesday June 01, 2016 @11:44PM (#11820217)
What is that mythical "universal algorithm" ?