The Extrapolation of Elementary Sequences

By: Nasa, National Aeronautics and Space Adm

We study sequence extrapolation as a stream-learning problem. Input examples are a stream of data elements of the same type (integers, strings, etc.), and the problem is to construct a hypothesis that both explains the observed sequence of examples and extrapolates the rest of the stream. A primary objective -- and one that distinguishes this work from previous extrapolation algorithms -- is that the same algorithm be able to extrapolate sequences over a variety of different types, including integers, strings, and trees. We define a generous family of constructive data types, and define as our learning bias a stream language called elementary stream descriptions. We then give an algorithm that extrapolates elementary descriptions over constructive datatypes and prove that it learns correctly. For freely-generated types, we prove a polynomial time bound on descriptions of bounded complexity. An especially interesting feature of this work is the ability to provide quantitative measures of confidence in competing hypotheses, using a Bayesian model of prediction. Laird, Philip and Saul, Ronald Unspecified Center ...

• Format: Paperback
• Language: English
• ISBN: 1726809390
• ISBN13: 9781726809399
• Release Date: January 1
• Publisher: Independently Published
• Length: 30 Pages
• Weight: 0.21 lbs.
• Dimensions: 0.1" x 8.5" x 11.0"