Warning: Table './science/watchdog' is marked as crashed and should be repaired query: INSERT INTO watchdog (uid, type, message, variables, severity, link, location, referer, hostname, timestamp) VALUES (0, 'php', '%message in %file on line %line.', 'a:4:{s:6:\"%error\";s:7:\"warning\";s:8:\"%message\";s:138:\"realpath(): open_basedir restriction in effect. File(/tmp) is not within the allowed path(s): (/var/www/html/science/science.uni-obuda.hu)\";s:5:\"%file\";s:60:\"/var/www/html/science/science.uni-obuda.hu/includes/file.inc\";s:5:\"%line\";i:200;}', 3, '', 'http://science.uni-obuda.hu/node/4803', '', '216.73.216.122', 1761898569) in /var/www/html/science/science.uni-obuda.hu/includes/database.mysql.inc on line 135 Warning: Table './science/watchdog' is marked as crashed and should be repaired query: INSERT INTO watchdog (uid, type, message, variables, severity, link, location, referer, hostname, timestamp) VALUES (0, 'php', '%message in %file on line %line.', 'a:4:{s:6:\"%error\";s:7:\"warning\";s:8:\"%message\";s:138:\"realpath(): open_basedir restriction in effect. File(/tmp) is not within the allowed path(s): (/var/www/html/science/science.uni-obuda.hu)\";s:5:\"%file\";s:60:\"/var/www/html/science/science.uni-obuda.hu/includes/file.inc\";s:5:\"%line\";i:200;}', 3, '', 'http://science.uni-obuda.hu/node/4803', '', '216.73.216.122', 1761898569) in /var/www/html/science/science.uni-obuda.hu/includes/database.mysql.inc on line 135 Fuzzy Flip-Flop Based Neural Network as a Function Approximator | science.uni-obuda.hu
Ugrás a tartalomra

Fuzzy Flip-Flop Based Neural Network as a Function Approximator

CímFuzzy Flip-Flop Based Neural Network as a Function Approximator
Közlemény típusaConference Paper
Kiadás éve2008
Kiadás nyelveEnglish
Oldalszám44-49
SzerzőkLovassy, R., L. T. Kóczy, and L. Gál
Konferencia neveIEEE International Conference on Computational Intelligence for Measurment Systems and Applications CIMSA
Konferencia helyszíneIstanbul, Turkey
Összefoglalás

Artificial neural networks and fuzzy logic systems, in the context of approximate reasoning, share common features and techniques. A family of fuzzy flip-flops is proposed, based on an artificial neural network-like structure which is suitable for approximating many-input one-output nonlinear functions. The neurons in the multilayer perceptron networks typically employ sigmoidal activation functions. The next state of the fuzzy J-K flip-flops (F3) using Yager and Dombi operators present quasi-S-shaped characteristics. The paper proposes the investigation of the possibility of constructing multilayer perceptrons from such fuzzy units. Each of the two candidates for F3-based neurons is examined for its training capability by evaluating and comparing the approximation properties in the context of different transcendental functions with one-input and multi-input cases. Simulation results are presented.