I think you need to define regularization. L1/L2? Yes those are old.
Drop out itself IS fairly new[1]. As well as its newer cousin drop connect.
I agree neural nets themselves are basically just a crazier parametric model. Many of the things we do to modify the gradient are applicable to logistic and other simpler regression techniques as well.
Drop out itself IS fairly new[1]. As well as its newer cousin drop connect.
I agree neural nets themselves are basically just a crazier parametric model. Many of the things we do to modify the gradient are applicable to logistic and other simpler regression techniques as well.
[2]: https://cs.nyu.edu/~wanli/dropc/dropc.pdfhttp://www.cs.toron...