• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) °áÇÕµÈ ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼ö¸¦ ÀÌ¿ëÇÑ ¿ÏÀü¿¬°á½Å°æ¸ÁÀÇ ¼º´É Çâ»ó
¿µ¹®Á¦¸ñ(English Title) Performance Improvement Method of Fully Connected Neural Network Using Combined Parametric Activation Functions
ÀúÀÚ(Author) °í¿µ¹Î   À̺ØÇ×   °í¼±¿ì   Young Min Ko   Peng Hang Li   Sun Woo Ko  
¿ø¹®¼ö·Ïó(Citation) VOL 11 NO. 01 PP. 0001 ~ 0010 (2022. 01)
Çѱ۳»¿ë
(Korean Abstract)
¿ÏÀü¿¬°á½Å°æ¸ÁÀº ´Ù¾çÇÑ ¹®Á¦¸¦ ÇØ°áÇϴµ¥ ³Î¸® »ç¿ëµÇ°í ÀÖ´Ù. ¿ÏÀü¿¬°á½Å°æ¸Á¿¡¼­ ºñ¼±ÇüÈ°¼ºÇÔ¼ö´Â ¼±Çüº¯È¯ °ªÀ» ºñ¼±Çü º¯È¯ÇÏ¿© Ãâ·ÂÇÏ´Â ÇÔ¼ö·Î½á ºñ¼±Çü ¹®Á¦¸¦ ÇØ°áÇϴµ¥ Áß¿äÇÑ ¿ªÇÒÀ» ÇÏ¸ç ´Ù¾çÇÑ ºñ¼±ÇüÈ°¼ºÇÔ¼öµéÀÌ ¿¬±¸µÇ¾ú´Ù. º» ¿¬±¸¿¡¼­´Â ¿ÏÀü¿¬°á½Å°æ¸ÁÀÇ ¼º´ÉÀ» Çâ»ó½Ãų ¼ö ÀÖ´Â °áÇÕµÈ ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼ö¸¦ Á¦¾ÈÇÑ´Ù. °áÇÕµÈ ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼ö´Â °£´ÜÈ÷ ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼öµéÀ» ´õÇÔÀ¸·Î½á ¸¸µé¾î³¾ ¼ö ÀÖ´Ù. ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼ö´Â ÀԷµ¥ÀÌÅÍ¿¡ µû¶ó È°¼ºÇÔ¼öÀÇ Å©±â¿Í À§Ä¡¸¦ º¯È¯½ÃÅ°´Â ÆĶó¹ÌÅ͸¦ µµÀÔÇÏ¿© ¼Õ½ÇÇÔ¼ö¸¦ ÃÖ¼ÒÈ­ÇÏ´Â ¹æÇâÀ¸·Î ÃÖÀûÈ­ÇÒ ¼ö ÀÖ´Â ÇÔ¼öÀÌ´Ù. ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼öµéÀ» °áÇÕÇÔÀ¸·Î½á ´õ¿í ´Ù¾çÇÑ ºñ¼±Çü°£°ÝÀ» ¸¸µé¾î³¾ ¼ö ÀÖÀ¸¸ç ¼Õ½ÇÇÔ¼ö¸¦ ÃÖ¼ÒÈ­ÇÏ´Â ¹æÇâÀ¸·Î ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼öµéÀÇ ÆĶó¹ÌÅ͸¦ ÃÖÀûÈ­ÇÒ ¼ö ÀÖ´Ù. MNIST ºÐ·ù¹®Á¦¿Í Fashion MNIST ºÐ·ù¹®Á¦¸¦ ÅëÇÏ¿© °áÇÕµÈ ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼öÀÇ ¼º´ÉÀ» ½ÇÇèÇÏ¿´°í ±× °á°ú ±âÁ¸¿¡ »ç¿ëµÇ´Â ºñ¼±ÇüÈ°¼ºÇÔ¼ö, ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼öº¸´Ù ¿ì¼öÇÑ ¼º´ÉÀ» °¡ÁüÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Deep neural networks are widely used to solve various problems. In a fully connected neural network, the nonlinear activation function is a function that nonlinearly transforms the input value and outputs it. The nonlinear activation function plays an important role in solving the nonlinear problem, and various nonlinear activation functions have been studied. In this study, we propose a combined parametric activation function that can improve the performance of a fully connected neural network. Combined parametric activation functions can be created by simply adding parametric activation functions. The parametric activation function is a function that can be optimized in the direction of minimizing the loss function by applying a parameter that converts the scale and location of the activation function according to the input data. By combining the parametric activation functions, more diverse nonlinear intervals can be created, and the parameters of the parametric activation functions can be optimized in the direction of minimizing the loss function. The performance of the combined parametric activation function was tested through the MNIST classification problem and the Fashion MNIST classification problem, and as a result, it was confirmed that it has better performance than the existing nonlinear activation function and parametric activation function.
Å°¿öµå(Keyword) ¿ÏÀü¿¬°á½Å°æ¸Á   ºñ¼±ÇüÈ°¼ºÇÔ¼ö   °áÇÕµÈ ÆĶó¸ÞÆ®¸¯ È°¼ºÇÔ¼ö   ÇнÀ   Fully Connected Neural Network   Nonlinear Activation Function   Combined Parametric Activation Function   Learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå