[B! machine learning] funayama1116ã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯

funayama1116 id:funayama1116

machine learningã«é–¢ã™ã‚‹funayama1116ã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯ (8)

${{author_name}}$

{{{comment_expanded}}}

{{label}}

{{#is_bookmark}}ãƒªã‚¹ãƒˆ{{/is_bookmark}}{{^is_bookmark}}ãƒªãƒ³ã‚¯{{/is_bookmark}}

${{author_name}}$
{{author_name}}{{created}}
{{ #comment }}{{ comment }}{{ /comment }}
- {{ label }}

${{author_name}}$

{{{comment_expanded}}}

{{label}}

{{#is_bookmark}}ãƒªã‚¹ãƒˆ{{/is_bookmark}}{{^is_bookmark}}ãƒªãƒ³ã‚¯{{/is_bookmark}}

j3.info | å†™çœŸãƒ¡ã‚¤ãƒ³ã§ã®ã‚“ã³ã‚Šç¶´ã‚‰ã‚Œã‚‹æ—¥è¨˜
ã ã„ã¶æ™‚é–“ãŒã‹ã‹ã‚Šã¾ã—ãŸãŒã€HG 1/550 ãƒŽã‚¤ã‚¨ãƒ»ã‚¸ãƒ¼ãƒ«å®Œæˆã—ã¾ã—ãŸã€‚ ã“ã®ã‚ãƒƒãƒˆã¯ã€ãƒãƒªã‚ãƒ£ãƒƒãƒ—ã‚’ä½¿ã‚ãšã«ã€ã¯ã•ã¿ã“ã‚“ã§ã„ãè¨è¨ˆã§ã™ã€‚ãªã®ã§ã€ãã®ã¾ã¾çµ„ã‚€ã¨ã€ä¾‹ãˆã°ã€è…•å…¨ä½“ã¨æœ¬ä½“ãŒå¤–ã›ãªããªã‚Šã¾ã™ã€‚å¾Œãƒãƒ¡åŠ å·¥ã‚’ã™ã‚‹æ‰‹ã‚‚ã‚ã‚Šã¾ã™ãŒã€ãƒãƒªã‚ãƒ£ãƒƒãƒ—ã‚’é©å®œçµ„ã¿è¾¼ã‚“ã§ã„ãã‚ˆã†ã«ã—ã¾ã—ãŸã€‚ å‰é¢ã¨èƒŒé¢ã€‚å½¢æˆè‰²ã‚ˆã‚Šã‚„ã‚„æš—ã‚ã«å¡—è£…ã—ã¾ã—ãŸã€‚ä»–ã€ç´°ã‹ããƒ‡ã‚£ãƒ†ã‚£ãƒ¼ãƒ«ã‚¢ãƒƒãƒ—ã—ã¾ã—ãŸã€‚ ã‚µãƒ–ã‚¢ãƒ¼ãƒ ã‚’è£…å‚™ã—ã¦ã€åˆ¥è§’åº¦ã€‚ã‚µãƒ–ã‚¢ãƒ¼ãƒ ã¯å¡—è£…ã ã‘ã§ã€ç„¡æ”¹é€ ã€‚ ã‚«ãƒ¡ãƒ©ã‚¢ã‚¤ã¯ã€ãƒ—ãƒ©æ£’ã§ä½œã‚Šç›´ã—ã¦ã€ã‚·ãƒ«ãƒãƒ¼ï¼‹ã‚¯ãƒªã‚¢ãƒ¼ã‚ªãƒ¬ãƒ³ã‚¸å¡—è£…ã—ãŸã®ã§ã€ã†ã¾ããƒ©ã‚¤ãƒˆã‚¢ãƒƒãƒ—ã™ã‚‹ã¨åå°„ã—ã¾ã™ã€‚ ã‚«ãƒ¡ãƒ©ã‚¢ã‚¤ä»¥å¤–ã«å¤§ããã„ã˜ã£ãŸã®ã¯ã€è‚©ã®ä¸Šéƒ¨ã‚’åˆ‡ã‚Šé›¢ã—ã¦å¤§åž‹åŒ–ã€ãƒãƒ¼ãƒ‹ã‚¢ã‚’è¿½åŠ ã€è…°ã®ãƒ‘ã‚¤ãƒ—ã‚’ã‚´ãƒ ç·šï¼‹ãƒ‘ã‚¤ãƒ—ãƒ‘ãƒ¼ãƒ„ã§ä½œã‚Šç›´ã—ã¨ã„ã†ã¨ã“ã‚ã§ã™ã€‚ã‚¹ã‚¸å½«ã‚Šã‚’ç´°ã‹ãå¢—ã‚„ã™åŠ å·¥ã¯ã‚ã¾ã‚Šå¥½ã¿ã§ã¯ãªã„ï¼ˆã¦ã„ã†ã‹å‡ºæ¥ãªã„ï¼‰ã®ã§ã€æŽ§ãˆã‚ã«ã—ã¾ã—ãŸã€‚ å¾Œã¯ã€é©å½“ã«ä½•æžšã‹ã€‚
funayama1116 2009/12/26
machine learning

trouble
ãƒªãƒ³ã‚¯
SVM-Light: Support Vector Machine
SVMlight Support Vector Machine Author: Thorsten Joachims <[email protected]> Cornell University Department of Computer Science Developed at: University of Dortmund, Informatik, AI-Unit Collaborative Research Center on 'Complexity Reduction in Multivariate Data' (SFB475) Version: 6.02 Date: 14.08.2008 Overview SVMlight is an implementation of Support Vector Machines (SVMs) in C. The main featu
funayama1116 2009/12/25
machine learning
ãƒªãƒ³ã‚¯
Momma's Wiki: SupportVectorMachine/SVMlight - æ‰‹è»½ã«è©¦ã›ã‚‹Support Vector Machine SVM-Ligh...
svm_learn svm_learn [options] example_file model_file ã§å¦ç¿’ã™ã‚‹ã€‚ example_fileã¯å¾Œã§èª¬æ˜Žã™ã‚‹æ›¸å¼ã«å¾“ã£ã¦è¨˜è¿°ã—ãŸãƒ†ã‚ã‚¹ãƒˆãƒ•ã‚¡ã‚¤ãƒ«ã§ã€model_fileã¯å¦ç¿’çµæžœã‚’åŽã‚ã‚‹ãƒ•ã‚¡ã‚¤ãƒ«ã§svm_learnãŒä½œã‚‹ã‚‚ã®ãªã®ã§é©å½“ãªåå‰ã‚’æŒ‡å®šã™ã‚‹ã ã‘ã§è‰¯ã„ã€‚ ã¤ã¾ã‚Šmodel_fileã‚’ä¿å˜ã—ã¦ãŠã‘ã°å¦ç¿’çŠ¶æ…‹ã‚’ç‹¬ç«‹ã—ã¦ç®¡ç†ã§ãã‚‹ã€‚ ã‚ªãƒ—ã‚·ãƒ§ãƒ³ã«é–¢ã—ã¦ã¯åŸºæœ¬çš„ã«-cã‚ªãƒ—ã‚·ãƒ§ãƒ³ã—ã‹å¼„ã‚‰ãªã„ã§è‰¯ã•ãã†ã€‚-cã«æ¸¡ã™æ•°å€¤ãŒå¤§ãããªã‚‹ã»ã©ãƒžãƒ¼ã‚¸ãƒ³ã‚’åºƒãã¨ã‚‹ãŒå¦ç¿’ã«æ™‚é–“ã‚’è¦ã™ã‚‹ã€‚ ã¡ãªã¿ã«-zã‚ªãƒ—ã‚·ãƒ§ãƒ³ã¯å‹•ä½œãƒ¢ãƒ¼ãƒ‰ã®é¸æŠžã§ã€åˆ†é¡žã€å›žå¸°ã€ãƒ©ãƒ³ã‚ãƒ³ã‚°ãŒé¸ã¹ã‚‹ã€‚ example_fileã®æ›¸å¼ <target> <feature>:<value> <feature>:<value> ... <feature>:<value> # <info> <targ
funayama1116 2009/12/25
machine learning
ãƒªãƒ³ã‚¯
SVM-Light(ã‚ªãƒ—ã‚·ãƒ§ãƒ³ã€ä½¿ã„æ–¹)
ã“ã“ã§ã¯ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢SVM-Lightã®ä½¿ã„æ–¹ã‚’èª¬æ˜Žã—ã¾ã™ã€‚SVMè‡ªä½“ã®åŽŸç†ã‚’çŸ¥ã‚ŠãŸã„æ–¹ã¯ã€ŒChris Burgeæ°ã®ãƒãƒ¥ãƒ¼ãƒˆãƒªã‚¢ãƒ«ã€ãŒè‰¯ã„æ•™ç§‘æ›¸ã¨ãªã‚‹ã§ã—ã‚‡ã†ã€‚ SVM-Lightã¯å¦ç¿’ãƒ¢ã‚¸ãƒ¥ãƒ¼ãƒ«(svm_learn)ã¨è˜åˆ¥ãƒ¢ã‚¸ãƒ¥ãƒ¼ãƒ«(svm_classify)ã§æ§‹æˆã•ã‚Œã¦ã„ã¾ã™ã€‚ã“ã®è˜åˆ¥ãƒ¢ã‚¸ãƒ¥ãƒ¼ãƒ«ã¯ã€å¦ç¿’ã•ã‚ŒãŸãƒ¢ãƒ‡ãƒ«ã‚’æ–°ãŸãªã‚µãƒ³ãƒ—ãƒ«ã«é©ç”¨ã™ã‚‹ã“ã¨ãŒå‡ºæ¥ã¾ã™ã€‚è©³ã—ãã¯ä»¥ä¸‹ã«ç¤ºã™ã€Œsvm_learnã€ã¨ã€Œsvm_classifyã€ã®ä½¿ã„æ–¹ã‚’å‚ç…§ã—ã¦ãã ã•ã„ã€‚ svm_learn svm_learnã¯æ¬¡ã®ã‚ˆã†ãªãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ã«ã‚ˆã£ã¦å‘¼ã³å‡ºã•ã‚Œã¾ã™ã€‚
funayama1116 2009/12/25
machine learning
ãƒªãƒ³ã‚¯
SVMã«ãŠã‘ã‚‹2æ¬¡è¨ˆç”»å•é¡Œã®è§£æ³•ã«å¯¾ã™ã‚‹è€ƒå¯Ÿ
SVMã® 2æ¬¡è¨ˆç”»å•é¡Œã«é–¢ã™ã‚‹è§£æ³•ã®è€ƒå¯Ÿ æ±äº¬ç†ç§‘å¤§å¦å·¥å¦éƒ¨çµŒå–¶å·¥å¦ç§‘ æ²¼ç”°ç ”ç©¶å®¤ 4400079 æˆ¸ç”°å¥ä¸€ å’æ¥ç ”ç©¶ç™ºè¡¨ 1 ç™ºè¡¨æ§‹æˆ 1. ã¯ã˜ã‚ã« 2. ã‚¯ãƒ©ã‚¹åˆ¤åˆ¥ã¨SVM 2-1. ã‚¯ãƒ©ã‚¹åˆ¤åˆ¥å•é¡Œ 2-2. ã‚µãƒãƒ¼ãƒˆãƒ™ã‚¯ã‚¿ãƒ¼ãƒžã‚·ãƒ³ 2-3. ç·šå½¢åˆ†é›¢ä¸å¯èƒ½ãªå ´åˆã®SVM 2-4. éžç·šå½¢SVM 3. 4. 5. 6. 7. Sequential Minimal Optimization(SMO) 2æ®µéšŽSMO å®Ÿé¨“ å®Ÿé¨“çµæžœï¼Œè€ƒå¯Ÿ ã¾ã¨ã‚ å‚è€ƒæ–‡çŒ® 2 1.ã¯ã˜ã‚ã« ãƒ‘ã‚¿ãƒ¼ãƒ³èªè˜å•é¡Œã«ãŠã‘ã‚‹ã‚¯ãƒ©ã‚¹åˆ¤åˆ¥æ‰‹æ³•ï¼š ã‚µãƒãƒ¼ãƒˆãƒ™ã‚¯ã‚¿ãƒ¼ãƒžã‚·ãƒ³(SVM)[1],æŠ„éŒ²[3] SVMï¼š2æ¬¡è¨ˆç”»å•é¡Œã‚’è§£ã â†’ãƒ‡ãƒ¼ã‚¿ãŒå¤šããªã‚‹ã«ã¤ã‚Œã¦è¨ˆç®—é‡ãŒéžå¸¸ã«å¤šããªã‚‹ Sequential Minimal Optimization (SMO) [2],[3],æŠ„éŒ²[1],[2]ï¼š SVMã«ã‚ˆã‚‹2æ¬¡è¨ˆç”»å•
funayama1116 2009/10/13
machine learning
ãƒªãƒ³ã‚¯
classifiers.lazy.LWL - weka wiki - Seesaa Wikiï¼ˆã‚¦ã‚£ã‚ï¼‰
funayama1116 2009/10/13
machine learning
ãƒªãƒ³ã‚¯
ã‚¹ãƒšã‚¯ãƒˆãƒ©ãƒ«ã‚¯ãƒ©ã‚¹ã‚¿ãƒªãƒ³ã‚°ã¯æ¬¡å…ƒåœ§ç¸®ã—ãªãŒã‚‰Kmeansã™ã‚‹æ‰‹æ³• - æ¦è”µé‡Žæ—¥è¨˜
æ©Ÿæ¢°å¦ç¿’ç³»ã®ã‚¨ãƒ³ãƒˆãƒªã‚’ç¶šã‘ã¦æ›¸ã„ã¦ã¿ã‚‹ã€‚ã‚¯ãƒ©ã‚¹ã‚¿ãƒªãƒ³ã‚°ã«ã¤ã„ã¦çŸ¥ã‚‰ãªã„äººã¯ä»¥ä¸‹ã®ã‚¨ãƒ³ãƒˆãƒªèªã‚“ã§ã‚‚ã¡ã‚“ã·ã‚“ã‹ã‚“ã·ã‚“ã ã¨æ€ã†ã®ã§ã€ã‚¯ãƒ©ã‚¹ã‚¿ãƒªãƒ³ã‚°ã¨ã„ã†æ¦‚å¿µã«ã¤ã„ã¦ã¯çŸ¥ã£ã¦ã„ã‚‹ã‚‚ã®ã¨ã™ã‚‹ã€‚ ãã‚Œã§ã€ä»Šæ—¥ã¯ã‚¹ãƒšã‚¯ãƒˆãƒ©ãƒ«ã‚¯ãƒ©ã‚¹ã‚¿ãƒªãƒ³ã‚°ã®è©±ã€‚è‡ªç„¶è¨€èªžå‡¦ç†ä»¥å¤–ã§ã‚‚åˆ©ç”¨ã•ã‚Œã¦ã„ã‚‹ãŒã€ã“ã‚Œã¯ã‚°ãƒ©ãƒ•ã®ã‚¹ãƒšã‚¯ãƒˆãƒ«ã«åŸºã¥ãã‚¯ãƒ©ã‚¹ã‚¿ãƒªãƒ³ã‚°ã®æ‰‹æ³•ã§ã€åŠæ•™å¸«ã‚ã‚Šå¦ç¿’ã¸ã®æ‹¡å¼µãŒã‚„ã‚Šã‚„ã™ã„ã®ãŒåˆ©ç‚¹ã€‚ãªã«ã‚’ã™ã‚‹ã‹ã¨ã„ã†ã¨ã‚¯ãƒ©ã‚¹ã‚¿ãƒªãƒ³ã‚°ã‚’ã‚°ãƒ©ãƒ•ã®åˆ†å‰²å•é¡Œ(ç–Žã§ã‚ã‚‹ã‚¨ãƒƒã‚¸ã‚’ã‚«ãƒƒãƒˆ)ã«å¸°ç€ã—ã¦è§£ãæ‰‹æ³•ã§ã€ã©ã†ã„ã†ãµã†ã«åˆ†å‰²ã™ã‚‹ã‹ã«ã‚ˆã£ã¦ Normalized cut (Ncut) ã¨ã‹ Min-max cut (Mcut) ã¨ã‹ã„ã‚ã„ã‚ã‚ã‚‹ã€‚ å®Œå…¨ã«ã‚°ãƒ©ãƒ•ãŒåˆ†å‰²ã§ãã‚‹å ´åˆã¯ã“ã‚Œã§ã‚ã§ãŸã—ã‚ã§ãŸã—ãªã®ã ãŒã€å®Ÿä¸–ç•Œã®ã‚°ãƒ©ãƒ•ã¯ãã‚“ãªç°¡å˜ã«åˆ‡ã‚Œãªã„ã“ã¨ãŒå¾€ã€…ã«ã—ã¦ã‚ã‚‹ã€‚ãã‚Œã§è¿‘ä¼¼ã—ã¦ã“ã®ã‚°ãƒ©ãƒ•åˆ†å‰²å•é¡Œã‚’è§£ãã®ã ãŒã€Normalized c
funayama1116 2009/10/12
NLP

machine learning
ãƒªãƒ³ã‚¯
çµ±è¨ˆçš„æ©Ÿæ¢°å¦ç¿’ | Nakagawa Lab.
çµ±è¨ˆçš„æ©Ÿæ¢°å¦ç¿’ çµ±è¨ˆçš„æ©Ÿæ¢°å¦ç¿’ã¨ã¯ã€è¦³æ¸¬ã•ã‚ŒãŸãƒ‡ãƒ¼ã‚¿ã‹ã‚‰çµ±è¨ˆçš„æ‰‹æ³•ã‚’ç”¨ã„æ–°ãŸãªçŸ¥è˜ã‚’å°Žå‡ºã™ã‚‹ã“ã¨ã§ã‚ã‚‹ã€‚ çµ±è¨ˆçš„æ©Ÿæ¢°å¦ç¿’ã«ã¤ã„ã¦ã®æ•™ç§‘æ›¸çš„ãªå†…å®¹ã¯ã“ã¡ã‚‰ã‚’å‚ç…§ã—ã¦ã»ã—ã„ã€‚ çµ±è¨ˆçš„æ©Ÿæ¢°å¦ç¿’ã«ã¯ç¨®ã€…ã®åˆ†é¡žãŒã‚ã‚‹ã€‚ä¸»è¦ãªã‚‚ã®ã‚’èª¬æ˜Žã—ã‚ˆã†ã€‚ æ•™å¸«ã‚ã‚Šå¦ç¿’ã¨æ•™å¸«ãªã—å¦ç¿’ æ•™å¸«ã‚ã‚Šå¦ç¿’(supervised learning)ã§ã¯ã€è¦³æ¸¬ãƒ‡ãƒ¼ã‚¿ã¨ã€ãã®ãƒ‡ãƒ¼ã‚¿ã®æ„å‘³ãŒä¸Žãˆã‚‰ã‚Œã‚‹ã€‚ä¾‹ãˆã°ã€æ–‡æ›¸åˆ†é¡žå•é¡Œã§ã‚ã‚Œã°ã€è¦³æ¸¬ã•ã‚ŒãŸæ–‡æ›¸ã¨ãã®æ–‡æ›¸ã®å±žã™ã‚‹ã‚«ãƒ†ã‚´ãƒªãƒ¼ï¼ˆã‚¹ãƒãƒ¼ãƒ„ã€èŠ¸èƒ½ã€ãªã©ï¼‰ã®å¯¾ã®ãƒ‡ãƒ¼ã‚¿é›†åˆï¼ˆã“ã‚Œã‚’training dataã¨å‘¼ã¶ã€‚)ã§ã‚ã‚‹ã€‚å¦ç¿’ã«ã‚ˆã£ã¦ã€è¦³æ¸¬ãƒ‡ãƒ¼ã‚¿ã®æŒã¤å±žæ€§ã¨æ„å‘³ã®é–¢ä¿‚ã‚’æŽ¨å®šã—ã€æœªçŸ¥ã®ãƒ‡ãƒ¼ã‚¿(ã“ã‚Œã‚’ test dataã€€ã¨å‘¼ã¶ã€‚ï¼‰ãŒä¸Žãˆã‚‰ã‚Œã‚‹ã¨ã€ãã®ãƒ‡ãƒ¼ã‚¿ã®æ„å‘³ã‚’å‡ºåŠ›ã™ã‚‹ã€‚ æ•™å¸«ãªã—å¦ç¿’(un-supervised learning)ã§ã¯ã€è¦³æ¸¬ãƒ‡ãƒ¼ã‚¿ã ã‘ãŒä¸Žãˆã‚‰ã‚Œã‚‹ã€‚è¦³æ¸¬ãƒ‡ãƒ¼ã‚¿ãŸã¡ã®
funayama1116 2009/03/21
machine learning
ãƒªãƒ³ã‚¯
1