'How to find the function's equation using Neural Network (Jupyter notebook)

I'm looking for some guidance as apparently there isn't too much information about it. I would like to know, if there's any documentation available to extract an function's equation from a given a dataset, or if someone can guide me how to obtain the equation to get all the points from a given data.

I know there are 2 methods:

  • Universal Approximation Universal Approximation.
  • Regression using Neural Networks

In both cases, it seems that doesn't fits what I need do it. Basically I have this function:

Function

In which I would like to obtain an equation that satisfies this function F(x) = ?

Reducing the noise, I got the following graph:

Smooth graph

My question is: is it possible to obtain a function through the graph only?

The input data is just a velocity vector in kilometers per hour.



Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source