• 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 > 2018³â Ãá°èÇмú´ëȸ

2018³â Ãá°èÇмú´ëȸ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ³»ºÎ FC ÃþÀ» °®´Â »õ·Î¿î CNN ±¸Á¶ÀÇ ¼³°è
¿µ¹®Á¦¸ñ(English Title) Design of new CNN structure with internal FC layer
ÀúÀÚ(Author) ¹Úȸ¹®   ¹Ú¼ºÂù   Ȳ±¤º¹   ÃÖ¿µ±Ô   ¹ÚÁøÇö   Hee-mun Park   Sung-chan Park   Kwang-bok Hwang   Young-kiu Choi   Jin-hyun Park  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 01 PP. 0233 ~ 0233 (2018. 05)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù À̹ÌÁö ÀνÄ, ¿µ»ó ÀνÄ, À½¼º ÀÓ½Ä, ÀÚ¿¬¾î ó¸® µî ´Ù¾çÇÑ ºÐ¾ß¿¡ ÀΰøÁö´ÉÀÌ Àû¿ëµÇ¸é¼­ µö·¯´×(Deep Learning) ±â¼ú¿¡ °üÇÑ °ü½ÉÀÌ ³ô¾ÆÁö°í ÀÖ´Ù. µö·¯´× Áß¿¡¼­µµ °¡Àå ´ëÇ¥ÀûÀÎ ¾Ë°í¸®ÁòÀ¸·Î À̹ÌÁö ÀÎ½Ä ¹× ºÐ·ù¿¡ °­Á¡ÀÌ ÀÖ°í °¢ ºÐ¾ß¿¡ ¸¹ÀÌ ¾²ÀÌ°í ÀÖ´Â CNN(Convolutional Neural Network)¿¡ ´ëÇÑ ¸¹Àº ¿¬±¸°¡ ÁøÇàµÇ°í ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ÀϹÝÀûÀÎ CNN ±¸Á¶¸¦ º¯ÇüÇÑ »õ·Î¿î ³×Æ®¿öÅ© ±¸Á¶¸¦ Á¦¾ÈÇÏ°íÀÚ ÇÑ´Ù. ÀϹÝÀûÀÎ CNN ±¸Á¶´Â convolution layer, pooling layer, fully-connected layer·Î ±¸¼ºµÈ´Ù. ±×·¯¹Ç·Î º» ¿¬±¸¿¡¼­´Â ÀϹÝÀûÀÎ CNN ±¸Á¶ ³»ºÎ¿¡ FC¸¦ ÷°¡ÇÑ »õ·Î¿î ³×Æ®¿öÅ©¸¦ ±¸¼ºÇÏ°íÀÚ ÇÑ´Ù. ÀÌ·¯ÇÑ º¯ÇüÀº ÄÁº¼·ç¼ÇµÈ À̹ÌÁö¿¡ ½Å°æȸ·Î¸ÁÀÌ °®´Â ÀåÁ¡ÀÎ ÀϹÝÈ­ ±â´ÉÀ» Æ÷ÇÔ½ÃÄÑ Á¤È®µµ¸¦ ¿Ã¸®°íÀÚ ÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, artificial intelligence has been applied to various fields such as image recognition, image recognition speech recognition, and natural language processing, and interest in Deep Learning technology is increasing. Many researches on Convolutional Neural Network(CNN), which is one of the most representative algorithms among Deep Learning, have strong advantages in image recognition and classification and are widely used in various fields. In this paper, we propose a new network structure that transforms the general CNN structure. A typical CNN structure consists of a convolution layer, ReLU layer, and a pooling layer. Therefore in this paper, We intend to construct a new network by adding fully connected layer inside a general CNN structure. This modification is intended to increase the learning and accuracy of the convoluted image by including the generalization which is an advantage of the neural network.
Å°¿öµå(Keyword) Convolutional Neural Network   convolution layer   ReLU layer   pooling layer  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå