Function Learning from Interpolation
Anthony, Martin; Bartlett, Peter
Description
In this paper, we study a statistical property of classes of real-valued functions that we call approximation from interpolated examples. We derive a characterization of function classes that have this property, in terms of their 'fat-shattering function', a notion that has proved useful in computational learning theory. The property is central to a problem of learning real-valued functions from random examples in which we require satisfactory performance from every algorithm that returns a...[Show more]
Collections | ANU Research Publications |
---|---|
Date published: | 2000 |
Type: | Journal article |
URI: | http://hdl.handle.net/1885/90355 |
Source: | Combinatorics Probability and Computing |
Download
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 19 May 2020/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator