It has been improved significantly in the past few years, but it does still tend to lag the papers themselves.
I think even that is overstating how useful it. For example, I think we can all agree that regularization is a huge and very important topic in ML for years. Here is the Wiki entry: https://en.wikipedia.org/wiki/Regularization_(mathematics)#Other_uses_of_regularization_in_statistics_and_machine_learning. Or interpretability: https://en.wikipedia.org/wiki/Explainable_artificial_intelligence . Things like layer normalization are not even mentioned anywhere. Pretty useless for learning about neural nets.
yeah, fair enough.
It has been improved significantly in the past few years, but it does still tend to lag the papers themselves.
I think even that is overstating how useful it. For example, I think we can all agree that regularization is a huge and very important topic in ML for years. Here is the Wiki entry: https://en.wikipedia.org/wiki/Regularization_(mathematics)#Other_uses_of_regularization_in_statistics_and_machine_learning. Or interpretability: https://en.wikipedia.org/wiki/Explainable_artificial_intelligence . Things like layer normalization are not even mentioned anywhere. Pretty useless for learning about neural nets.
yeah, fair enough.