Generalized Information

Communications of the Blyth Institute Pub Date : 2019-06-02 DOI:10.33014/issn.2640-5652.1.2.bartlett.1

Jonathan Bartlett

引用次数: 4

Abstract

Generalized Information (GI) is a measurement of the degree to which a program can be said to generalize a dataset. It is calculated by creating a program to model the data set, measuring the Active Information in the model, and subtracting out the size of the model. Active Information allows GI to be usable with both exact and inexact models.

查看原文本刊更多论文

广义的信息

广义信息(GI)是对一个程序可以泛化一个数据集的程度的度量。它是通过创建一个程序来对数据集建模，测量模型中的活动信息，并减去模型的大小来计算的。活动信息允许GI可用于精确模型和不精确模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Communications of the Blyth Institute

自引率

0.00%

发文量