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

»çÀÌÆ®¸Ê

Loading..

Please wait....

Çмú´ëȸ ÇÁ·Î½Ãµù

Ȩ Ȩ > ¿¬±¸¹®Çå > Çмú´ëȸ ÇÁ·Î½Ãµù > Çѱ¹Á¤º¸Åë½ÅÇÐȸ Çмú´ëȸ > 2019³â Ãá°èÇмú´ëȸ

2019³â Ãá°èÇмú´ëȸ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) GANÀ» È°¿ëÇÑ ºÐ·ù ½Ã½ºÅÛ¿¡ °üÇÑ ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Study on Classification System using Generative Adversarial Networks
ÀúÀÚ(Author) ¹è»óÁß   ÀÓº´¿¬   Á¤ÁöÇР  ³ªÃ¶ÈÆ   Á¤È¸°æ   Sangjung Bae   Byeongyeon Lim   Jihak Jung   Chulhun Na   Hoekyung Jung  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 01 PP. 0338 ~ 0340 (2019. 05)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ³×Æ®¿öÅ©ÀÇ ¹ß´Þ·Î ÀÎÇØ µ¥ÀÌÅÍ°¡ ÃàÀûµÇ´Â ¼Óµµ¿Í Å©±â°¡ Áõ°¡µÇ°í ÀÖ´Ù. ÀÌ µ¥ÀÌÅ͵éÀ» ºÐ·ùÇϴµ¥ ¸¹Àº ¾î·Á¿òÀÌ Àִµ¥ ±× ¾î·Á¿ò Áß¿¡ Çϳª°¡ ¶óº§¸µÀÇ ¾î·Á¿òÀÌ´Ù. ¶óº§¸µÀº º¸Åë »ç¶÷ÀÌ ÁøÇàÇÏ°Ô µÇ´Âµ¥ ¸ðµç »ç¶÷ÀÌ °°Àº ¹æ½ÄÀ¸·Î µ¥ÀÌÅ͸¦ ÀÌÇظ¦ Çϴµ¥ ¹«¸®°¡ ÀÖ¾î µ¿ÀÏÇÑ ±âÁØÀ¸·Î ¶óº§¸µ ÇÏ´Â °ÍÀº ¸Å¿ì ¾î·Æ´Ù´Â ¹®Á¦°¡ ÀÖ´Ù. À̸¦ ÇØ°áÇϱâ À§ÇØ º» ³í¹®¿¡¼­´Â GANÀ» ÀÌ¿ëÇÏ¿© ÀÔ·Â À̹ÌÁö¸¦ ±â¹ÝÀ¸·Î »õ·Î¿î À̹ÌÁö¸¦ »ý¼ºÇÏ°í À̸¦ ÇнÀÀ» ÇÏ´Â µ¥ »ç¿ëÀ» ÇÏ¿© ÀÔ·Â µ¥ÀÌÅ͸¦ °£Á¢ÀûÀ¸·Î ÇнÀÇÒ ¼ö ÀÖ°Ô ±¸ÇöÇÏ¿´´Ù. À̸¦ ÅëÇØ ÇнÀ µ¥ÀÌÅÍÀÇ °³¼ö¸¦ ´Ã·Á ºÐ·ùÀÇ Á¤È®µµ¸¦ ³ôÀÏ ¼ö ÀÖÀ» °ÍÀ¸·Î »ç·áµÈ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, the speed and size of data accumulation are increasing due to the development of networks. There are many difficulties in classifying these data. One of the difficulties is the difficulty of labeling. Labeling is usually done by people, but it is very difficult for everyone to understand the data in the same way and it is very difficult to label them on the same basis. In order to solve this problem, we implemented GAN to generate new image based on input image and to learn input data indirectly by using it for learning. This suggests that the accuracy of classification can be increased by increasing the number of learning data.
Å°¿öµå(Keyword) Classification System   DCGAN   GAN   Machine Learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå