arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.07161cs.LO
收藏

一种“黑箱”分类器系统的逻辑

A Logic of "Black Box" Classifier Systems

Xinghan Liu, Emiliano Lorini

AI总结:

针对机器学习二分类器的黑箱不透明性,本文提出乘积模态逻辑PLC,将黑箱解释为分类器集合上的不确定性,并给出公理化、可满足性复杂性结果及支持信息更新的动态扩展。

摘要:

传统上,二分类器通过命题逻辑(PL)进行研究。PL只能将它们表示为白箱,其前提是底层布尔函数完全已知。然而,实际应用中使用并由机器学习训练得到的二分类器是不透明的,通常被描述为黑箱。在本文中,我们提出了一种称为PLC(用于二值输入分类器的乘积模态逻辑,Product modal Logic for binary input Classifier)的乘积模态逻辑,其中“黑箱”概念被解释为一组分类器之上的不确定性。我们给出了关于该逻辑的公理化以及可满足性检查复杂性的结果。此外,我们还提出了一种动态扩展,在其中可以表示获取关于实际分类器的新信息的过程。

英文摘要:

Binary classifiers are traditionally studied by propositional logic (PL). PL can only represent them as white boxes, under the assumption that the underlying Boolean function is fully known. Binary classifiers used in practical applications and trained by machine learning are however opaque. They are usually described as black boxes. In this paper, we provide a product modal logic called PLC (Product modal Logic for binary input Classifier) in which the notion of "black box" is interpreted as the uncertainty over a set of classifiers. We give results about axiomatics and complexity of satisfiability checking for our logic. Moreover, we present a dynamic extension in which the process of acquiring new information about the actual classifier can be represented.

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。

↑