Inferability of recursive real-valued functions
Inductive inference is the study of suitable methods to identify a function \(f\) given sequences of observed data of the form \((x, f(x))\) as information to an inference machine. This paper studies the modifications to the standard set-up if real-valued functions have to be identified. An algorithm is presented that approximately infers real-valued functions from numerical data with some error bounds. It is shown that (i) the class of elementary functions with real coefficients is inferrable and (ii) the class of real-valued functions whose domains are the same rational interval is approximately inferrable if the class itself is r.e. and the intervals need not be closed. Finally, the precision of the guesses produced by the inference machine is discussed in the case that sufficient data have not been given. For the entire collection see [Zbl 0877.00015].
- On the inductive inference of recursive real-valued functions
- On the inference of semi-coherent structures from data
- Learning figures with the Hausdorff metric by fractals -- towards computable binary classification
- Prediction of Recursive Real-Valued Functions from Finite Examples
- scientific article; zbMATH DE number 1301795 (Why is no real title available?)
- A comparison of identification criteria for inductive inference of recursive real-valued functions
This page was built for publication: Inferability of recursive real-valued functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4370214)
