Knowledge-Based Neurocomputing: A Fuzzy Logic Approach

2009
ISBN: 978-3-540-88076-9
Verlag: Springer Berlin Heidelberg

Buch, Englisch, 100 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 348 g

Reihe: Studies in Fuzziness and Soft Computing

In this monograph, the authors introduce a novel fuzzy rule-base, referred to as the They show that inferring the FARB, using standard tools from fuzzy logic theory, yields an input-output map that is mathematically equivalent to that of an artificial neural network. Conversely, every standard artificial neural network has an equivalent FARB.

The FARB-ANN equivalence integrates the merits of symbolic fuzzy rule-bases and sub-symbolic artificial neural networks, and yields a new approach for in artificial neural networks.

Zielgruppe

Research

Autoren/Hrsg.

Margaliot, Michael

Kolman, Eyal

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Fuzzy-Systeme
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Wissensbasierte Systeme, Expertensysteme
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Neuronale Netzwerke

Inhaltsverzeichnis

The FARB.- The FARB–ANN Equivalence.- Rule Simplification.- Knowledge Extraction Using the FARB.- Knowledge-Based Design of ANNs.- Conclusions and Future Research.