Hi, I have two variables x and y and the functional relationship between x and y is like: y=x^2+log(x). My question is that is it possible to apply some method to reconstruct the functional form based on the training data that is generated from it? I understand that there are many methods for regresstion but none of them can predict the functions that consist of operators. For example in R: x=seq(1:100) y=x^2+log(x) result=somemodel(x,y) summary(result) The output of the method is ideally a mathematical equation that fits to the training data, e.g.
y=x^2+log(x)
Any ideas will be appreciated! Best, Jing