From Weighted Conditionals of Multilayer Perceptrons to a Gradual Argumentation Semantics

10/07/2021
by   Laura Giordano, et al.
0

A fuzzy multipreference semantics has been recently proposed for weighted conditional knowledge bases, and used to develop a logical semantics for Multilayer Perceptrons, by regarding a deep neural network (after training) as a weighted conditional knowledge base. This semantics, in its different variants, suggests some gradual argumentation semantics, which are related to the family of the gradual semantics. The relationships between weighted conditional knowledge bases and MLPs extend to the proposed gradual semantics, which captures the stationary states of MPs, so that a dee neural network can as well be seen as a weighted argumentation graph.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/24/2020

Weighted defeasible knowledge bases and a multipreference semantics for a deep neural network model

In this paper we investigate the relationships between a multipreferenti...
research
04/29/2023

A preferential interpretation of MultiLayer Perceptrons in a conditional logic with typicality

In this paper we investigate the relationships between a multipreferenti...
research
09/17/2021

Weighted Conditional EL^bot Knowledge Bases with Integer Weights: an ASP Approach

Weighted knowledge bases for description logics with typicality have bee...
research
02/02/2022

An ASP approach for reasoning on neural networks under a finitely many-valued semantics for weighted conditional knowledge bases

Weighted knowledge bases for description logics with typicality have bee...
research
06/01/2021

On the KLM properties of a fuzzy DL with Typicality

The paper investigates the properties of a fuzzy logic of typicality. Th...
research
07/10/2021

From Common Sense Reasoning to Neural Network Models through Multiple Preferences: an overview

In this paper we discuss the relationships between conditional and prefe...
research
07/11/2002

Compilation of Propositional Weighted Bases

In this paper, we investigate the extent to which knowledge compilation ...

Please sign up or login with your details

Forgot password? Click here to reset