Curried error function, which gets a target value
and returns a differentiable function that represents
some sort of error between the input and the target value.
To be able to speak about differentiability, we need some
underlying vector space V. To be able to speak about
errors, we need some metric there. In this version,
we simply require that all subclasses of the error
function work with everything that looks like Real^n.
Curried error function, which gets a target value and returns a differentiable function that represents some sort of error between the input and the target value.
To be able to speak about differentiability, we need some underlying vector space V. To be able to speak about errors, we need some metric there. In this version, we simply require that all subclasses of the error function work with everything that looks like Real^n.