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

Studienarbeiten

• Themenvorschläge für Studien- und Abschlussarbeiten
• Abgeschlossene Arbeiten
  • Algebra und Diskrete Strukturen
  • Automatentheorie
  • Computational Logic
  • Knowledge-aware Artificial Intelligence
  • Logische Programmierung und Argumentation
  • Verifikation und formale quantitative Analyse
  • Wissensbasierte Systeme
• Laufende Studienarbeiten

Toggle side column

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

Bachelorarbeit, Studienarbeit von Valentin Mayer-Eichberger

•   Betreuer Steffen Hölldobler, Sebastian Bader
•   Wissensverarbeitung
•   24. Januar 2006 – 24. Januar 2006
•   Download

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.