Re:Wide and Deep Learning: Better Together with TensorFlow
by argonaut on Wednesday June 29, 2016 @11:49PM
(#12006434)
Yeah, this is a pretty good point. IMO it's a major flaw in the paper that they didn't empirically compare their new model to other models (like just an ensemble, as you mention), though they do discuss it.
I wouldn't be surprised if a simple ensemble performs better!
I wouldn't be surprised if a simple ensemble performs better!