• 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 > 2016³â Ãß°èÇмú´ëȸ

2016³â Ãß°èÇмú´ëȸ

Current Result Document : 16 / 20 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Convolutional Neural Network¿Í Monte Carlo Tree Search¸¦ ÀÌ¿ëÇÑ ÀΰøÁö´É ¹ÙµÏ ÇÁ·Î±×·¥ÀÇ ±¸Çö
¿µ¹®Á¦¸ñ(English Title) Implementation of Artificial Intelligence Computer Go Program Using a Convolutional Neural Network and Monte Carlo Tree Search
ÀúÀÚ(Author) ±âö¹Î   Á¶ÅÂÈÆ   Cheol-min Ki   Tai-Hoon Cho  
¿ø¹®¼ö·Ïó(Citation) VOL 20 NO. 02 PP. 0405 ~ 0408 (2016. 10)
Çѱ۳»¿ë
(Korean Abstract)
¹ÙµÏ, ü½º, Àå±â¿Í °°Àº °ÔÀÓÀº »ç¶÷µéÀÇ µÎ³ú¹ß´Þ¿¡ µµ¿òÀ» ÁÖ¾î¿Ô´Ù. ÀÌ °ÔÀÓµéÀº ÄÄÇ»ÅÍ ÇÁ·Î±×·¥À¸·Îµµ °³¹ßµÇ¾úÀ¸¸ç, È¥ÀÚ¼­µµ °ÔÀÓÀ» Áñ±æ ¼ö ÀÖµµ·Ï ¸¹Àº ¾Ë°í¸®ÁòµéÀÌ °³¹ßµÇ¾ú´Ù. »ç¶÷À» À̱â´Â ü½º ÇÁ·Î±×·¥Àº 1990³â´ë¿¡ °³¹ßµÈ °Í¿¡ ºñÇØ ¹ÙµÏÀº °æ¿ìÀÇ ¼ö°¡ ³Ê¹« ¸¹¾Æ¼­ ÇÁ·Î ¹ÙµÏ±â»ç¸¦ À̱â±â´Â ºÒ°¡´ÉÇÑ °ÍÀ¸·Î ¿©°ÜÁ³´Ù. ÇÏÁö¸¸ MCTS(Monte Carlo Tree Search)¿Í CNN(Convolutional Neural Network)ÀÇ ÀÌ¿ëÀ¸·Î ¹ÙµÏ ¾Ë°í¸®ÁòÀÇ ¼º´ÉÀº Å« Çâ»óÀ» ÀÌ·ç¾ú´Ù. º» ³í¹®¿¡¼­´Â CNN°ú MCTS¸¦ »ç¿ëÇÏ¿© ¹ÙµÏ ¾Ë°í¸®ÁòÀÇ °³¹ßÀ» ÁøÇàÇÏ¿´´Ù. ¹ÙµÏÀÇ ±âº¸°¡ ÇнÀµÈ CNNÀ» ÀÌ¿ëÇÏ¿© ÃÖÀûÀÇ ¼ö¸¦ ã°í, MCTS¸¦ ÀÌ¿ëÇÏ¿© °ÔÀÓÀÇ ½Ã¹Ä·¹À̼ÇÀ» ÁøÇàÇÏ¿© À̱æ È®·üÀ» °è»êÇÑ´Ù. ¶ÇÇÑ ±âÁ¸ ±âº¸¸¦ ÀÌ¿ëÇÏ¿© ¹ÙµÏÀÇ ÆÐÅÏ Á¤º¸¸¦ ÃßÃâÇÏ°í, À̸¦ ÀÌ¿ëÇÏ¿© ¼Óµµ¿Í ¼º´É Çâ»óÀ» µµ¸ðÇÏ¿´´Ù. ÀÌ ¹æ¹ýÀº ÀϹÝÀûÀ¸·Î »ç¿ëµÇ´Â ¹ÙµÏ ¾Ë°í¸®Áòµé¿¡ ºñÇØ ¼º´É Çâ»óÀÌ ÀÖ¾ú´Ù. ¶ÇÇÑ ÃæºÐÇÑ Computing Power°¡ Á¦°øµÇ¸é ´õ¿í ¼º´ÉÀÌ Çâ»óµÉ °ÍÀ¸·Î º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
Games like Go, Chess, Janggi have helped to brain development of the people. These games are developed by computer program. And many algorithms have been developed to allow myself to play. The person winning chess program was developed in the 1990s. But game of go is too large number of cases. So it was considered impossible to win professional go player. However, with the use of MCTS(Monte Carlo Tree Search) and CNN(Convolutional Neural Network), the performance of the go algorithm is greatly improved. In this paper, using CNN and MCTS were proceeding development of go algorithm. Using the manual of go learning CNN look for the best position, MCTS calculates the win probability in the game to proceed with simulation. In addition, extract pattern information of go using existing manual of go, plans to improve speed and performance by using it. This method is showed a better performance than general go algorithm. Also if it is receiving sufficient computing power, it seems to be even more improved performance.
Å°¿öµå(Keyword) Machine Learning   Convolutional Neural Network   Monte Carlo Tree Search   Computer Go  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå