[psandersen]

DNN's make good features though, especially if you have time series data or lots of text.

I agree that the final model should be a randomforest/xgboost/lightgbm for typical tabular data.

[mlthoughts2018]

I meant that extracting an intermediate layer as a feature embedding and then sticking a classical model on top of it performs worse than curating features through domain-specific expert tuning, for a ton of diverse application domains.