Not your computer? Use a private browsing window to sign in. Learn more about using Guest mode
Not your computer? Use a private browsing window to sign in. Learn more about using Guest mode
Deep learningåå¼·ä¼20130208 Presentation Transcript Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase DetectionRichard Socher, Eric H. Huang, Jeffrey Pennington, Andrew Y. Ng, Christopher D. ManningComputer Science Department, Stanford University, Stanford, CA 94305, USA SLAC National Accelerator Laboratory, Stanford University, Stanford, CA 94309, USA (NIPS 2011) 02/08 2013 D1 å¤§ç¥ æ£
Jubatus : ãªã³ã©ã¤ã³æ©æ¢°å¦ç¿åãåæ£å¦çãã¬ã¼ã ã¯ã¼ã¯Â¶ Jubatusã¯ãåæ£ãããã¼ã¿ããã常ã«ç´ æ©ãããæ·±ãåæããããã¨ãçã£ãåæ£åºç¤æè¡ã§ãã Jubatusã®ååã®ç±æ¥ã¯ãä¿æãªåç©ã§ãããã¼ã¿ã®å¦è¡åããã®å½åã§ããã¦ãã¿ã¹ãã¨èªã¿ã¾ããæ ªå¼ä¼ç¤¾Preferred Networksã¨NTTã½ããã¦ã§ã¢ã¤ããã¼ã·ã§ã³ã»ã³ã¿ãå ±åéçºãããæ¥æ¬çºã®ãªã¼ãã³ã½ã¼ã¹ãããã¯ãã§ãã æçµçã«å ¨ã¦ã®äººã«ã¹ã±ã¼ã©ãã«ãªãªã³ã©ã¤ã³æ©æ¢°å¦ç¿ãã¬ã¼ã ã¯ã¼ã¯ãæä¾ãããã¨ãJubatusã®ç®æ¨ã§ãã Jubatus ã¯ä»¥ä¸ã®ç¹å¾´ãæã£ããªã³ã©ã¤ã³æ©æ¢°å¦ç¿åãåæ£å¦çãã¬ã¼ã ã¯ã¼ã¯ã§ãã ãªã³ã©ã¤ã³æ©æ¢°å¦ç¿ã©ã¤ãã©ãª: å¤å¤åé¡ãç·å½¢å帰ãæ¨è¦ï¼è¿åæ¢ç´¢ï¼ãã°ã©ããã¤ãã³ã°ãç°å¸¸æ¤ç¥ãã¯ã©ã¹ã¿ãªã³ã° ç¹å¾´ãã¯ãã«å¤æå¨ (fv_converter): ãã¼ã¿ã®åå¦çã¨ç¹å¾´æ½åº ãã©ã«ã
ããã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥éãã®åå¼·ä¼åç»ã ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãºããã«ããæçãªã·ãªã¼ãºã åç»ãªã¹ãï¼ååï¼ ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第1å@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第1å ãã®1@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第1å ãã®2@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第1å ãã®3@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é第2å@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第2å ãã®1@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第2å ãã®2@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第2å ãã®3@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第2å ãã®4@ã¯ã¼ã¯ã¹ã¢ããªã±ã¼ã·ã§ã³ãº ãã¿ã¼ã³èªèã¨æ©æ¢°å¦ç¿å ¥é 第3å ãã®1 @ã¯ã¼
3. ILSVRC 2012 大è¦æ¨¡ç©ä½èªèã®ã³ã³ãã¹ã http://www.image-net.org/challenges/LSVRC/2012/ Classification Localization Team name Error Team name Error 1 Super Vision 0.15315 1 Super Vision 0.335463 2 Super Vision Deep LearningVision 0.16422 2 Super 0.341905 3 ISI 0.26172 3 OXFORD_VGG 0.500342 4 ISI 0.26602 4 OXFORD_VGG 0.50139 5 ISI 0.26646 5 OXFORD_VGG 0.522189 6 ISI 0.26952 6 OXFORD_VGG 0.529482 7 OXFORD_VGG
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
å¦çãå®è¡ä¸ã§ã
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}