It is neat- the need to look at the second derivative in "Optimal Brain Damage" ...

jmount on Feb 16, 2016 | parent | context | favorite | on: An introduction to variable and feature selection ...

It is neat- the need to look at the second derivative in "Optimal Brain Damage" (because we know the first derivatives will be zero due to the use of optimization) also underlies Fisher information https://en.wikipedia.org/wiki/Fisher_information .