You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I still love your work and found a good paper: Neural networks and rational functions
It describes that rational functions can approximate arbitrary functions better than polynomials. That made me think that the gplearn should generate 2 separate polynomials in parallel and use the ratio of them as the function approximate.
My argument is the following (without exactly knowing the proof of theorems):
it is proven that a neural network with non-linear activations can approximate any function
it is proven in this paper that a rational function (functions represented as the ratio of two polynomials) can approximate any RELU neural network (which is nonlinear)
==>
so the rational functions can approximate any functions
I'm not sure that the performance or the size will be optimal, but I think it worth a try. What do you think?
guyko
The text was updated successfully, but these errors were encountered:
Hi @trevorstephens ,
I still love your work and found a good paper:
Neural networks and rational functions
It describes that rational functions can approximate arbitrary functions better than polynomials. That made me think that the gplearn should generate 2 separate polynomials in parallel and use the ratio of them as the function approximate.
My argument is the following (without exactly knowing the proof of theorems):
==>
I'm not sure that the performance or the size will be optimal, but I think it worth a try. What do you think?
guyko
The text was updated successfully, but these errors were encountered: