TY - GEN
T1 - Neural networks=Fuzzy rule bases
AU - Kolman, Eyal
AU - Margaliot, Michael
PY - 2004
Y1 - 2004
N2 - We introduce a novel Mamdani-type fuzzy model, referred to as the allpermutations fuzzy rule-base (APFRB). We show that any standard feedforward neural network is mathematically equivalent to an appropriate APFRB. This implies that we can easily extract the knowledge embedded in a trained neural network in the form of fuzzy rules.
AB - We introduce a novel Mamdani-type fuzzy model, referred to as the allpermutations fuzzy rule-base (APFRB). We show that any standard feedforward neural network is mathematically equivalent to an appropriate APFRB. This implies that we can easily extract the knowledge embedded in a trained neural network in the form of fuzzy rules.
UR - http://www.scopus.com/inward/record.url?scp=8844243888&partnerID=8YFLogxK
U2 - 10.1142/9789812702661_0023
DO - 10.1142/9789812702661_0023
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:8844243888
SN - 9812388737
SN - 9789812388735
T3 - Applied Computational Intelligence - Proceedings of the 6th International FLINS Conference
SP - 111
EP - 117
BT - Applied Computational Intelligence - Proceedings of the 6th International FLINS Conference
PB - World Scientific Publishing Co. Pte Ltd
T2 - Applied Computational Intelligence - Proceedings of the 6th International FLINS Conference
Y2 - 1 September 2004 through 3 September 2004
ER -