Title :
Fuzzy and chaotic neuro-network modeling
Author :
Garliauskas, Algis
Author_Institution :
Lab. of Neuroinformatics, Inst. of Math. & Informatics, Vilnius, Lithuania
fDate :
6/23/1905 12:00:00 AM
Abstract :
The origin of fuzzy signals lies in the complex biochemical and electrical processes of the synapse and dendrite membrane excitation and in the inhibition mechanism. The mathematical operations included in fuzzy neural network modeling are described. The scalar product between the inputs of layers and synaptic weights is replaced by a fuzzy logic multiplication. The sum of products changes into fuzzy logic sums, and operators such as supremum, maximum and minimum are presented for fuzzy description. Both fuzzy properties and a chaos phenomenon are analyzed based on experimental computations
Keywords :
chaos; fuzzy neural nets; mathematical operators; modelling; biochemical processes; chaotic neuro-network modeling; dendrite membrane excitation; electrical processes; fuzzy backpropagation; fuzzy description; fuzzy logic multiplication; fuzzy logic sums; fuzzy membership; fuzzy neural network modeling; fuzzy signals; inhibition mechanism; mathematical operations; maximum operator; minimum operator; scalar product; supremum operator; synapse excitation; synaptic weights; Artificial neural networks; Biological neural networks; Biomembranes; Chaos; Fuzzy logic; Fuzzy neural networks; Fuzzy systems; Neural networks; Neurons; Signal processing;
Conference_Titel :
Fuzzy Systems, 2001. The 10th IEEE International Conference on
Conference_Location :
Melbourne, Vic.
Print_ISBN :
0-7803-7293-X
DOI :
10.1109/FUZZ.2001.1007340
