• 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 : 12 / 12

ÇѱÛÁ¦¸ñ(Korean Title) °èÃþÀû ±ºÁýÈ­¸¦ ÀÌ¿ëÇÑ ´Éµ¿Àû ÇнÀ
¿µ¹®Á¦¸ñ(English Title) Active Learning based on Hierarchical Clustering
ÀúÀÚ(Author) ¿ìÈ£¿µ   ¹ÚÁ¤Èñ   Hoyoung Woo   Cheong Hee Park  
¿ø¹®¼ö·Ïó(Citation) VOL 02 NO. 10 PP. 0705 ~ 0712 (2013. 10)
Çѱ۳»¿ë
(Korean Abstract)
´Éµ¿Àû ÇнÀ(active learning)Àº ¼Ò¼öÀÇ ¶óº§ µ¥ÀÌÅÍ·Î ±¸¼ºµÈ ÈÆ·Ã ÁýÇÕÀÌ ÁÖ¾îÁø °æ¿ì¿¡ ºÐ·ù±â ÇнÀ¿¡ °¡Àå µµ¿òÀÌ µÉ ¸¸ÇÑ ¾ð¶óº§µå µ¥ÀÌÅ͸¦ ¼±ÅÃÇÏ¿© Àü¹®°¡¿¡ ÀÇÇÑ ¶óº§¸µÀ» ÅëÇØ ÈÆ·Ã ÁýÇÕ¿¡ Æ÷ÇÔ½ÃÅ°´Â °úÁ¤À» ¹Ýº¹ÇÔÀ¸·Î½á ºÐ·ù±âÀÇ ¼º´ÉÀ» Çâ»ó½ÃÅ°´Â °ÍÀ» ¸ñÀûÀ¸·Î ÇÑ´Ù. º» ³í¹®¿¡¼­´Â ¿öµå ¿¬°á(ward¡¯s linkage)À» ÀÌ¿ëÇÑ °èÃþÀû ±ºÁýÈ­(hierarchical clustering)¸¦ ¹ÙÅÁÀ¸·Î ÇÑ ´Éµ¿Àû ÇнÀ ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈµÈ ¹æ¹ýÀº °¢ ±ºÁý¿¡¼­ Àû¾îµµ ÇϳªÀÇ »ùÇÃÀ» Æ÷ÇÔÇϵµ·Ï Ãʱâ ÈÆ·Ã ÁýÇÕÀ» ´Éµ¿ÀûÀ¸·Î ±¸¼ºÇϰųª ¶Ç´Â ±âÁ¸ÀÇ ÈÆ·Ã ÁýÇÕÀ» È®ÀåÇÔÀ¸·Î½á Àüü µ¥ÀÌÅÍ ºÐÆ÷¸¦ ¹Ý¿µÇÒ ¼ö ÀÖ°Ô ÇÑ´Ù. ±âÁ¸ÀÇ ´Éµ¿Àû ÇнÀ ¹æ¹ýµé Áß ´ëºÎºÐÀº Ãʱâ ÈÆ·Ã ÁýÇÕÀÌ ÁÖ¾îÁ® ÀÖÀ» °æ¿ì¸¦ °¡Á¤ÇÏ´Â ¹Ý¸é¿¡ Á¦¾ÈÇÏ´Â ¹æ¹ýÀº Ãʱâ Ŭ·¡½º Á¤º¸¸¦ °¡Áø ÈÆ·Ã µ¥ÀÌÅÍ°¡ ÁÖ¾îÁöÁö ¾ÊÀº °æ¿ì¿Í ÁÖ¾îÁø °æ¿ì¿¡ ¸ðµÎ Àû¿ë °¡´ÉÇÏ´Ù. ½ÇÇèÀ» ÅëÇÏ¿© Á¦¾ÈÇÏ´Â ¹æ¹ýÀÌ ºñ±³ ¹æ¹ýµé¿¡ ºñÇØ ºÐ·ù±â ¼º´ÉÀ» Å©°Ô Çâ»ó½Ãų ¼ö ÀÖ´Â È¿°úÀûÀÎ µ¥ÀÌÅÍ ¼±ÅÃÀ» ¼öÇàÇÔÀ» º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
Active learning aims to improve the performance of a classification model by repeating the process to select the most helpful unlabeled data and include it to the training set through labelling by expert. In this paper, we propose a method for active learning based on hierarchical agglomerative clustering using Ward's linkage. The proposed method is able to construct a training set actively so as to include at least one sample from each cluster and also to reflect the total data distribution by expanding the existing training set. While most of existing active learning methods assume that an initial training set is given, the proposed method is applicable in both cases when an initial training data is given or not given. Experimental results show the superiority of the proposed method.
Å°¿öµå(Keyword) ´Éµ¿Àû ÇнÀ   ±ºÁýÈ­   ¿öÁî ¹æ¹ý   Active Learning   Clustering  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå