<ul><li>The article introduces a neuro-symbolic approach that combines low-level perception with high-level reasoning tasks.</li><li>The goal is to determine the degree of possibility that an input instance belongs to a target concept.</li><li>Intermediate concepts are used for explanation purposes and to justify the classification of an input instance.</li><li>Efficient methods for defining the matrix relation and the equation system in a possibilistic rule-based system are also presented.</li></ul>

$\Pi$-NeSy: A Possibilistic Neuro-Symbolic Approach

Discover more