• 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¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document : 9 / 175 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ½Ã°è¿­ ½ÉÃþÇнÀ ¸ðµ¨ÀÇ Àº´Ð ³ëµå¿¡ ´ëÇÑ ½Ã°¢È­
¿µ¹®Á¦¸ñ(English Title) Visualization of Convolutional Neural Networks for Time Series Input Data
ÀúÀÚ(Author) Á¶¼ÒÈñ   ÃÖÀç½Ä   Sohee Cho   Jaesik Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 05 PP. 0445 ~ 0453 (2020. 05)
Çѱ۳»¿ë
(Korean Abstract)
»ê¾÷, ÀÇ·á, ±ÝÀ¶ µî ´Ù¾çÇÑ ºÐ¾ß¿¡¼­ ÀΰøÁö´ÉÀ» È°¿ëÇÑ ¿¹Ãø ¹× Áø´ÜÀÌ ´Ã¾î³ª¸é¼­, ÀΰøÁö´ÉÀÇ ³»ºÎ ÀÛµ¿¿ø¸®¸¦ ¼³¸íÇÏ´Â ¿¬±¸¿¡µµ °ü½ÉÀÌ ³ô¾ÆÁö°í ÀÖ´Ù. À̹ÌÁö µ¥ÀÌÅÍ¿¡¼­ Áß¿ä ÀԷ Ư¡Á¡À» ½Ã°¢È­ÇÏ´Â ±âÁ¸ ¿¬±¸µé°ú ´Ù¸£°Ô, º» ³í¹®¿¡¼­´Â ½Ã°è¿­ µ¥ÀÌÅÍÀÇ Àº´Ð ³ëµå¸¦ ½Ã°¢È­ÇÏ¿© ½ÉÃþ½Å°æ¸Á ³»ºÎÀÇ ÀÛµ¿¿ø¸®¸¦ ¼³¸íÇÑ´Ù. º» ³í¹®Àº Àº´Ð ³ëµåÀÇ ½Ã°¢È­¸¦ ½±°Ô Çϵµ·Ï °¡ÁßÄ¡ Çà·Ä(weight matrix)À» ±âÁØÀ¸·Î Àº´Ð ³ëµå¸¦ ±ºÁýÈ­ÇÏ¿© ÆÐÅÏÀ» ÆľÇÇÏ¿´´Ù. À̸¦ ÅëÇØ ½ÉÃþÇнÀ ¸ðµ¨ÀÇ ÀÛµ¿¿ø¸®¸¦ ¼³¸íÇÒ »Ó¸¸ ¾Æ´Ï¶ó, »ç¿ëÀÚ ¼öÁØ¿¡¼­ ½Ã°è¿­ µ¥ÀÌÅÍ¿¡ ´ëÇÑ ÀÌÇظ¦ ³ôÀÏ ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Globally, the use of artificial intelligence (AI) applications has increased in a variety of industries from manufacturing, to health care to the financial sector. As a result, there is a growing interest in explainable artificial intelligence (XAI), which can provide explanations of what happens inside AI. Unlike previous work using image data, we visualize hidden nodes for a time series. To interpret which patterns of a node make more effective model decisions, we propose a method of arranging nodes in a hidden layer. The hidden nodes sorted by weight matrix values show which patterns significantly affected the classification. Visualizing hidden nodes explains a process inside the deep learning model, as well as enables the users to improve their understanding of time series data.
Å°¿öµå(Keyword) ½Ã°è¿­ µ¥ÀÌÅÍ   ½ÉÃþÇнÀ   Àº´Ð ³ëµå   time series data   deep learning   hidden layers   weight matrix   patterns   °¡ÁßÄ¡ Çà·Ä   ÆÐÅÏ  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå