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:12:\"user warning\";s:8:\"%message\";s:173:\"Table './science/sessions' is marked as crashed and should be repaired\nquery: SELECT COUNT(sid) AS count FROM sessions WHERE timestamp >= 1781832551 AND uid = 0\";s:5:\"%file\";s:63:\"/var/www/html/science/science.uni-obuda.hu/includes/session.inc\";s:5:\"%line\";i:120;}', 3, '', 'http://science.uni-obuda.hu/node/4700', '', '216.73.216.140', 1781833451) 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:12:\"user warning\";s:8:\"%message\";s:184:\"Table './science/sessions' is marked as crashed and should be repaired\nquery: SELECT COUNT(DISTINCT s.uid) FROM sessions s WHERE s.timestamp >= 1781832551 AND s.uid > 0\";s:5:\"%file\";s:67:\"/var/www/html/science/science.uni-obuda.hu/modules/user/user.module\";s:5:\"%line\";i:776;}', 3, '', 'http://science.uni-obuda.hu/node/4700', '', '216.73.216.140', 1781833451) 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/4700', '', '216.73.216.140', 1781833451) 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/4700', '', '216.73.216.140', 1781833451) in /var/www/html/science/science.uni-obuda.hu/includes/database.mysql.inc on line 135 Hardware Implementable Neural Networks Based on Fuzzy Operators | science.uni-obuda.hu
Ugrás a tartalomra

Hardware Implementable Neural Networks Based on Fuzzy Operators

CímHardware Implementable Neural Networks Based on Fuzzy Operators
Közlemény típusaConference Paper
Kiadás éveSubmitted
Kiadás nyelveEnglish
Oldalszám8
SzerzőkLovassy, R., L. T. Kóczy, I. J. Rudas, and L. Gál
Konferencia neveWorld Conference on Soft Computing
Kiadás dátuma2011
Konferencia helyszíneSan Francisco State University, USA
Összefoglalás

In this paper we propose sigmoid function generators derived from fuzzy J-K and D flip-flops, and Fuzzy Flip-Flop based Neural Networks (FNNs) based on Dombi, Łukasiewicz, and a new pair of Trigonometric operations. An advantage of such FNNs is their easy hardware implementability, and they are more suitable to avoid overfitting than standard neural networks (e.g. tansig function based, MATLAB Neural Network Toolbox type) in the frame of simple function approximation problems. The experimental results show that these FNNs provide rather good generalization performance, with far better mathematical stability than the standard tansig based neural networks, and they are more suitable to avoid overfitting in the case of test data containing noisy items in the form of outliers.