Space of Reasons and Mathematical Model

TL;DR

This paper explores how inferential relations and implications in language can be modeled within neural networks, aiming to represent different types of explanations like causal and conceptual in a unified framework.

Contribution

It proposes a novel approach to represent implications and conceptual conditions in neural network models, bridging linguistic inference and computational modeling.

Findings

Implications of propositional logic can be integrated into neural network models.

Different kinds of explanations can be represented through model conditions.

A conceptual framework for modeling language implications is outlined.

Abstract

Inferential relations govern our concept use. In order to understand a concept it has to be located in a space of implications. There are different kinds of conditions for statements, i.e. that the conditions represent different kinds of explanations, e.g. causal or conceptual explanations. The crucial questions is: How can the conditionality of language use be represented. The conceptual background of representation in models is discussed and in the end I propose how implications of propositional logic and conceptual determinations can be represented in a model of a neural network.