Workshop in Logics for Multi-Agent Systems

Emiliano Lorini (IRIT, Université Paul Sabatier)

Title: A Logic of "Black Box" Classifier Systems (joint work with X. Liu)

Date and time: September 1st at 3 pm

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.

The Workshop invited talks and coffee break will take place in room MF105 at the Manufacture des Tabacs of the University Toulouse 1 Capitole.

See the detailed building map here (look for Building F).