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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÀûÀº ¾çÀÇ µ¥ÀÌÅÍ¿¡ Àû¿ë °¡´ÉÇÑ °èÃþº° µ¥ÀÌÅÍ Áõ°­ ¾Ë°í¸®Áò
¿µ¹®Á¦¸ñ(English Title) A layered-wise data augmenting algorithm for small sampling data
ÀúÀÚ(Author) Á¶ÈñÂù   ¹®Á¾¼·   Hee-chan Cho   Jong-sub Moon  
¿ø¹®¼ö·Ïó(Citation) VOL 20 NO. 06 PP. 0065 ~ 0072 (2019. 12)
Çѱ۳»¿ë
(Korean Abstract)
µ¥ÀÌÅÍ Áõ°­(Data Augmentation)Àº ÀûÀº ¾çÀÇ µ¥ÀÌÅ͸¦ ¹ÙÅÁÀ¸·Î ´Ù¾çÇÑ ¾Ë°í¸®ÁòÀ» ÅëÇØ µ¥ÀÌÅÍÀÇ ¾çÀ» ´Ã¸®´Â ±â¼úÀÌ´Ù. Çö½Ç¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ ±â°èÇнÀ ¹× µö·¯´× ±â¹ýÀ» »ç¿ëÇÏ´Â °æ¿ì, µ¥ÀÌÅÍ ¼ÂÀÌ ºÎÁ·ÇÑ °æ¿ì°¡ ¸¹´Ù. µ¥ÀÌÅÍÀÇ ºÎÁ·Àº ¸ðµ¨ ÇнÀ ½Ã, µ¥ÀÌÅÍ ¼ÂÀÇ Æ¯Â¡À» Àß ¹Ý¿µÇÏÁö ¸øÇÏ´Â °Í ÀÌ¿Ü¿¡µµ °ú¼ÒÀûÇÕ ¹× °úÀûÇÕ¿¡ ºüÁú À§ÇèÀÌ Å©´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â ¿ÀÅäÀÎÄÚ´õ¿Í °íÀ¯°ª ºÐÇظ¦ ±â¹ÝÀ¸·Î ÇÏ´Â µ¥ÀÌÅÍ Áõ°­ ±â¹ýÀ» ÅëÇØ µ¥ÀÌÅ͸¦ Áõ°­ ½ÃÅ°°í À̸¦ ½ÉÃþ ½Å°æ¸ÁÀÇ °¢ Ãþ ¸¶´Ù Àû¿ëÇÏ¿©, ½ÉÃþ ½Å°æ¸ÁÀ» È¿°úÀûÀ¸·Î »çÀü ÇнÀÇÏ´Â ¹æ¹ýÀ» Á¦½ÃÇÑ´Ù. ÀÌÈÄ, WOBC µ¥ÀÌÅÍ¿Í WDBC µ¥ÀÌÅÍ¿¡ ´ëÇØ ½ÇÇèÀ» ÅëÇÏ¿© ³í¹®¿¡¼­ Á¦¾ÈÇÏ´Â ¹æ¹ýÀÌ ºÐ·ù Á¤È®µµ¸¦ Çâ»ó½ÃÅ°´ÂÁö ÃøÁ¤ÇÏ°í ±âÁ¸ ¿¬±¸µé°ú ºñ±³ÇÔÀ¸·Î½á Á¦¾ÈÇÑ ¹æ¹ýÀÌ ½ÇÁúÀûÀ¸·Î Àǹ̰¡ ÀÖ´Â µ¥ÀÌÅ͸¦ »ý¼ºÇÏ°í ¸ðµ¨ÀÇ ÇнÀ¿¡ È¿°úÀûÀÓÀ» º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
Data augmentation is a method that increases the amount of data through various algorithms based on a small amount of sample data. When machine learning and deep learning techniques are used to solve real-world problems, there is often a lack of data sets. The lack of data is at greater risk of underfitting and overfitting, in addition to the poor reflection of the characteristics of the set of data when learning a model. Thus, in this paper, through the layer-wise data augmenting method at each layer of deep neural network, the proposed method produces augmented data that is substantially meaningful and shows that the method presented by the paper through experimentation is effective in the learning of the model by measuring whether the method presented by the paper improves classification accuracy.
Å°¿öµå(Keyword) µö·¯´×   µ¥ÀÌÅÍ Áõ°­   °íÀ¯°ª ºÐÇØ   Deep learning   data augmentation   Eigen decomposition  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå