Re:Sorting Two Tons of Lego, the Software Side
by minimaxir on Saturday May 06, 2017 @03:03PM
(#14281727)
> You're seeing hate for deep learning on HN!?!
Most of the hate for deep learning on HN is usually against using it in titles as clickbait. (i.e. just simply taking a pretrained/predefined model and changing the source dataset without any optimization)
The in-depth explanations of mechanics discussed in deep learning as noted in fast.ai courses and this submission do justify the use of the deep learning moniker, though.
Re:Sorting Two Tons of Lego, the Software Side
by deepnotderp on Saturday May 06, 2017 @05:40PM
(#14282424)
A pre trained deep net can work very well in a data limited domain if there's sufficient overlap.
Yes, but that's true of any ML approach.
Deep learning is great if you're dealing with a hugely dimensional problem, and you have the data to train the model. If one of those things is not true (and usually, one of those things is not true), you're better off starting simple.
Re:Sorting Two Tons of Lego, the Software Side
by jacquesm on Sunday May 07, 2017 @12:23PM
(#14286159)
That's an excellent point and one that kept me from trying the deep learning approach for a long time. But in the end the machine + rudimentary deep learning provided its own dataset and that really made it work.
So even if I didn't have the data to train the model I had enough data to bootstrap the process and sometimes that's all you need.
Yes, agreed. Your use case was interesting to me in the way that you bootstrapped the problem. If only more domains were like that!
But seriously: I think you're overstating the case. I've enjoyed watching the fast.ai videos, and I think deep learning is a clear choice for some areas right now. Many others, no.
If you're working in a data-limited domain, in particular (i.e. most of them) there are probably better first choices. I know plenty of folks who have used deep learning to achieve no better than comparable results to the simpler methods they were using before.
But yes, the initial engineering costs of a deep learning system have come down a lot further than I thought before I watched your videos.