Re:Why do tree-based models still outperform deep learning o...
by laichzeit0 on Thursday August 04, 2022 @04:23AM
(#32340536)
This is how I see it:
Statistical modeling: input -> feature extraction (manual) -> model selection (manual) -> output
Machine learning: input -> feature extraction (manual) -> model selection (auto) -> output
Deep learning: input -> feature extraction (auto) -> model selection (auto) -> output
So take a DL image classifier. The convolution + pooling layers perform automatic feature extraction. Back to OPs point, why use something like DL when you've already engineered your features?
Re:Why do tree-based models still outperform deep learning o...
by wpietri on Thursday August 04, 2022 @11:19AM
(#32344071)
Wow, what a good summary. Thanks!
One of the things that interests me about nominal AI applications is the extent to which they're sort of a Mechanical Turk or what I've heard called Artificial Artificial Intelligence. By which I mean it's sold as computer magic, but most of the magic is actually humans sneaking in a lot of human judgement. That can come through humans directly massaging the output or through human-driven selection of results. But I've also been wondering to what extent natural human intelligence is getting put in at the lower layers of the system, like feature engineering.