Extracting Propositional Logic Programs From Neural Networks: A Decompositional Approach.

From International Center for Computational Logic
Toggle side column

Extracting Propositional Logic Programs From Neural Networks: A Decompositional Approach.

Bachelor's thesis, project thesis by Valentin Mayer-Eichberger
Combining artificial neural networks and logic programming for machine

learning tasks is the main objective of neural symbolic integration. One important step towards practical applications in this field is the development of techniques for extracting symbolic knowledge from neural networks.

In this thesis a new extraction method is proposed and thoroughly investigated. It translates the class of feedforward networks with binary threshold functions into propositional logic programs by means of a decompositional approach.