A Logic of "Black Box" Classifier Systems - Logique, Interaction, Langue et Calcul Access content directly
Conference Papers Year : 2022

A Logic of "Black Box" Classifier Systems

Abstract

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.
Fichier principal
Vignette du fichier
BCLU - 2022-11-26T173224.539.pdf (581.3 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03873355 , version 1 (26-11-2022)

Identifiers

Cite

Xinghan Liu, Emiliano Lorini. A Logic of "Black Box" Classifier Systems. 28th Workshop on Logic, Language, Information and Computation (WOLLIC 2022), Sep 2022, Lasi, Romania. pp.158-174, ⟨10.1007/978-3-031-15298-6_10⟩. ⟨hal-03873355⟩
28 View
24 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More