Re:Deep Forest: Towards an Alternative to Deep Neural Networks
by jkbschwarz on Thursday March 02, 2017 @06:32AM
(#13773331)
To your point that they are comparing small datasets. I dont see that as a problem. If they achieve better results on small datasets that is a great achievement, as often the bottleneck is the size of the dataset rather than computation time.
[ Parent
| on HN ]
Re:Deep Forest: Towards an Alternative to Deep Neural Networks
by krona on Thursday March 02, 2017 @07:35AM
(#13773584)
> often the bottleneck is the size of the dataset rather than computation time
That's generally true for DNNs, which is a good place to be if you have lots of data. This typically isn't true for tree based approaches, which is why they fell out of fashion in some problem domains; they don't generalize as well. This paper doesn't seem to change what we already know in this respect.