Discussion about this post

User's avatar
Joshua Blake's avatar

You're confusing naive Bayes and the entirety of Bayesian statistics here. In the example given, you are correct that you cannot apply naive Bayes. But you can still have a Bayesian regression model and apply Bayes rule, you're just assuming a model. There's nothing special about deep learning here, it's just assuming a very complex and flexible model but you can frame it as a regression anyway.

Expand full comment
Jonathan's avatar

But isn't there a lot of arbitrariness in deep learning models?

We could train different models with different architectures and different hyper-parameters, and get different results, right? Why is this better than the "ad-hoc-ness" of the Bayesian approach?

Expand full comment
32 more comments...

No posts