• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÆÛÁö±ÔÄ¢À» ÀÌ¿ëÇÑ ½Å°æȸ·Î¸ÁÀÇ ÀÚµ¿ ±¸¼º
¿µ¹®Á¦¸ñ(English Title) The Automatic Topology Construction of The Neural Network using the Fuzzy Rule
ÀúÀÚ(Author) ÀÌÇö°ü   ÀÌÁ¤ÈÆ   ¾ö±âȯ   Hyun-kwan Lee   Jung-hoon Lee   Ki-hwan Eom  
¿ø¹®¼ö·Ïó(Citation) VOL 05 NO. 04 PP. 0766 ~ 0776 (2001. 07)
Çѱ۳»¿ë
(Korean Abstract)
´ÙÃþ ½Å°æȸ·Î¸ÁÀÇ ¸ðµ¨ÀÇ ±¸¼ºÀº Àû¿ëºÐ¾ß¿¡ µû¶ó¼­ ÀÓÀÇ·Î ¼±ÅõǾîÁö°í, ÃÖÀûÀÇ ¸ðµ¨ ±¸ ¼ºÀº ±ä ½Ã°£¿¡ °ÉÄ£ ½ÃÇàÂø¿À¸¦ ÅëÇÏ¿© °áÁ¤µÈ´Ù. º» ³í¹®¿¡¼­´Â ´ÙÃþ ½Å°æȸ·Î¸Á ¸ðµ¨ÀÇ Àº´ÐÃþ ´º·± ¼ö¸¦ ÇнÀ °úÁ¤¿¡¼­ ÆÛÁö ±ÔÄ¢À» ÀÌ¿ëÇÏ¿© ÃÖÀûÈ­ÇÏ´Â ¹æ½ÄÀ» Á¦¾ÈÇÏ¿´´Ù. ÀÓÀÇÀÇ ÆÐÅÏ ¹®Á¦¿Í µµ¸³ÁøÀÚÀÇ ¸ãÇο¡ Àû¿ëÇÏ¿© Á¦¾ÈÇÑ ¾Ë°í¸®ÁòÀÇ À¯¿ë¼ºÀ» ºñ±³ °ËÅäÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
In the constructing of the multi layer neural network, the network topology is often chosen arbitrarily for different applications, and the optimum topology of the network is determined by the long processing of the trial and error. In this paper, we propose the automatic topology construction using the fuzzy rule that optimizes the neurons of hidden layer, and prune the weights connecting the hidden layer and the output layer during the training process. The simulation of pattern recognition, and the experiment of the mapping of the inverted pendulum showed the effectiveness of the proposed method.
Å°¿öµå(Keyword)
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå