| タイトル | The Extrapolation of Elementary Sequences |
| 本文（外部サイト） | http://hdl.handle.net/2060/19960022276 |
| 著者（英） | Saul, Ronald; Laird, Philip |
| 著者所属（英） | NASA |
| 発行日 | 1992-10-01 |
| 言語 | eng |
| 内容記述 | 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. |
| NASA分類 | Behavioral Sciences |
| レポートNO | 96N25300
NASA-TM-111488
FIA-92-31
NAS 1.15:111488 |
| 権利 | No Copyright |
|
