arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0704.1043cs.CCcs.ITmath.IT
收藏

关于短序列的Kolmogorov-Chaitin复杂性

On the Kolmogorov-Chaitin Complexity for short sequences

Jean-Paul Delahaye, Hector Zenil

摘要:

Kolmogorov-Chaitin复杂度(K)作为从s到产生s的最短程序的函数的缺点是它的不可计算性,这限制了它的适用范围。此外,当字符串很短时,K对特定通用图灵机U的依赖性可以是任意的。在实践中,可以通过可计算的压缩方法来近似它。但是,这种压缩方法并不总是提供有意义的近似值--例如,对于比典型编译器长度更短的字符串。在本文中,我们提出了一个经验的方法来克服这个困难,并获得一个稳定的定义短序列的Kolmogorov-Chaitin复杂性。此外,分布频率方面的相关性被发现在两个模型的抽象机器,即一维元胞自动机和确定性图灵机的输出。

英文摘要:

A drawback of Kolmogorov-Chaitin complexity (K) as a function from s to the shortest program producing s is its noncomputability which limits its range of applicability. Moreover, when strings are short, the dependence of K on a particular universal Turing machine U can be arbitrary. In practice one can approximate it by computable compression methods. However, such compression methods do not always provide meaningful approximations--for strings shorter, for example, than typical compiler lengths. In this paper we suggest an empirical approach to overcome this difficulty and to obtain a stable definition of the Kolmogorov-Chaitin complexity for short sequences. Additionally, a correlation in terms of distribution frequencies was found across the output of two models of abstract machines, namely unidimensional cellular automata and deterministic Turing machine.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑