Neural-fuzzy controller with heterogeneous neurons

Chih Chi Chang*, Chung-Yong Tsai

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review


For engineering applications, complex pre-calculations may be necessary to evaluate the fuzzy degree of a simple linguistic term in the conditional part. A situation in which if these pre-calculations are excluded from the system would make, it will be difficult to discriminate the physical meaning of the rule from the neural nets. Therefore, this work applies feature extraction to replace these pre-calculations. The proposed neural fuzzy system extracts features by heterogeneous neurons. The proposed system's structure and its advantages are described in detailed. A controller designed by the proposed neural fuzzy system is presented as well.

Original languageEnglish
Number of pages4
StatePublished - 1 Dec 1999
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: 10 Jul 199916 Jul 1999


ConferenceInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA

Fingerprint Dive into the research topics of 'Neural-fuzzy controller with heterogeneous neurons'. Together they form a unique fingerprint.

Cite this