基于MML的(随机)逻辑理论复杂性评估工具
An MML-based tool for evaluating the complexity of (stochastic) logic theories
摘要:
理论评估是许多领域的关键问题:机器学习,科学发现,逆向工程,决策,软件工程,设计,人类科学等。如果我们有一套理论,能够解释同一组现象,我们需要一个标准来选择哪一个是最好的。当然,有许多可能的标准。模型简单性是理论评价中最常用的标准之一。最小消息长度(MML)是一种可靠的方法来评估理论相对于给定的证据或数据。理论可以用特定或一般(图灵完备)语言表达。一阶逻辑,特别是逻辑编程,是一种图灵完备语言。评估一个理论或图灵完备语言描述的程序的简单性,比仅仅计算行数或位数要困难得多。事实上,这是计算其柯尔莫哥洛夫复杂度的问题,这是不可计算的。文献中很少有作品能够为图灵完备语言提供准确有效的近似。在这项工作中,我们提出了第一个通用的MML编码方案的逻辑程序。有了这个方案,我们可以量化编码(或发送)一个理论、一组数据或给定理论的相同数据所需的信息位。作为上述方案的实现,我们提出了一个软件工具,它能够编码和评估一组替代(随机)理论(程序)对一组例子。我们说明了各种非概率和概率的情况下,该工具的应用。
英文摘要:
Theory evaluation is a key problem in many areas: machine learning, scientific discovery, inverse engineering, decision making, software engineering, design, human sciences, etc. If we have a set of theories that are able to explain the same set of phenomena, we need a criterion to choose which one is best. There are, of course, many possible criteria. Model simplicity is one of the most common criteria in theory evaluation. The Minimum Message Length (MML) is a solid approach to evaluate theories relative to a given evidence or data. Theories can be expressed in specific or general (Turing-complete) languages. First-order logic, and logic programming in particular, is a Turing-complete language. Evaluating the simplicity of a theory or program described in a Turing-complete language is much more difficult than just counting the number of lines or bits. It is, in fact, the problem of calculating its Kolmogorov complexity, which is uncomputable. Few works in the literature have been able to present accurate and effective approximations for a Turing-complete language. In this work, we present the first general MML coding scheme for logic programs. With this scheme, we can quantify the bits of information required to code (or send) a theory, a set of data or the same data given the theory. As a realization of the above-mentioned schemes, we present a software tool which is able to code and evaluate a set of alternative (stochastic) theories (programs) against a set of examples. We illustrate the application of the tool to a variety of non-probabilistic and probabilistic scenarios.
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。