Sometimes, requiring explanability is counterproductive

Re:Sometimes, requiring explanability is counterproductive by leereeves on Wednesday February 05, 2020 @04:34PM (#22251206)

Yann LeCun and others debated this for an hour at NeurIPS 2017.

https://www.youtube.com/watch?v=93Xv8vJ2acI

There's a lot of good points in there from both sides, but what really stuck with me is that given the choice between an explainable model and a black box model that works better (more accurate predictions), most people choose the black box model.

[ Parent | on HN ]

Re:Sometimes, requiring explanability is counterproductive by naresh_xai on Thursday February 06, 2020 @02:11AM (#22254086)

Which is strongly misleading tradeoff. For a ton of tasks, deep learning methods are no better than white box regression or tree ensemble methods.

And there is no reason to expect that a deep learning model has to be unexplainable. He’s putting up a mystical interpretability vs accuracy tradeoff which does not exist.

There is a ton of research out there making deep neural networks (slightly to significantly interpretable)

[ Parent | on HN ]

Re:Sometimes, requiring explanability is counterproductive by opless on Wednesday February 05, 2020 @08:49PM (#22252795)

I think your insight is a perfect description of humans authority bias.

People love to be told what to do. Even if in the face of overwhelming real world evidence people blindly follow their GPS, and to ignore it can cause a lot of stress.

[ Parent | on HN ]