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

dai_yamashita id:dai_yamashita

machine learningã«é–¢ã™ã‚‹dai_yamashitaã®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}}

GitHub - postgresml/postgresml: Postgres with GPUs for ML/AI apps.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert
dai_yamashita 2022/05/21
github

PostgreSQL

machine learning
ãƒªãƒ³ã‚¯
Reinforcement Learning for Torch: Introducing torch-twrl
Open source Reinforcement Learning for Torch: Introducing torch-twrl Advances in machine learning have been driven by innovations and ideas from many fields. Inspired by the way that humans learn, Reinforcement Learning (RL) is concerned with algorithms which improve with trial-and-error feedback to optimize future performance. Board games and video games often have well-defined reward functions w
dai_yamashita 2016/10/23
torchTwrl

machine learning

æ©Ÿæ¢°å¦ç¿’

lua
ãƒªãƒ³ã‚¯
SciRuby Machine Learning Current Status and Future
RubyKaigi 2016
dai_yamashita 2016/09/10
science

machine learning

slide

ruby
ãƒªãƒ³ã‚¯
[TensorFlowã§æ ªä¾¡äºˆæƒ³] 0 - Google ã®ã‚µãƒ³ãƒ—ãƒ«ã‚³ãƒ¼ãƒ‰ã‚’å‹•ã‹ã—ã¦ã¿ã‚‹ - Qiita
TensorFlowã§æ ªä¾¡äºˆæƒ³ã‚·ãƒªãƒ¼ã‚º 0 - Google ã®ã‚µãƒ³ãƒ—ãƒ«ã‚³ãƒ¼ãƒ‰ã‚’å‹•ã‹ã—ã¦ã¿ã‚‹ 1 - çµ‚å€¤ãŒå§‹å€¤ã‚ˆã‚Šã‚‚é«˜ããªã‚‹ã‹ã§åˆ¤å®šã—ã¦ã¿ã‚‹ 2 - æ—¥çµŒå¹³å‡225éŠ˜æŸ„ã®æ ªä¾¡äºˆæƒ³æ£è§£çŽ‡ãƒ©ãƒ³ã‚ãƒ³ã‚°ã€œ 3 - æ—¥æœ¬3506éŠ˜æŸ„ã®æ ªä¾¡äºˆæƒ³ãƒ©ãƒ³ã‚ãƒ³ã‚° 4 - å®Ÿéš›ã«å£²è²·ã—ãŸã‚‰å„²ã‹ã‚‹ã®ã‹ã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ã—ã¦ã¿ã‚‹ 5 - å¤§ããä¸ŠãŒã‚‹ã¨äºˆæƒ³ã•ã‚ŒãŸã¨ãã ã‘è²·ã£ã¦ã¿ã‚‹ã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ 6 - å¦ç¿’ãƒ‡ãƒ¼ã‚¿ã®é …ç›®ã‚’å¢—ã‚„ã™ï¼éš ã‚Œå±¤ã®ã‚µã‚¤ã‚ºã‚‚å¢—ã‚„ã™ï¼ 7 - æ ªä¾¡ãŒä½•%ä¸Šæ˜‡ã™ã‚‹ã¨äºˆæ¸¬ã—ãŸã‚‰è²·ãˆã°ã„ã„ã®ã‹ï¼Ÿ 8 - ã©ã®éŠ˜æŸ„ã‚’è²·ã†ã‹ 9 - å¹´åˆ©6.79% å‰ç½®ã çŒ«ã‚‚æ“åã‚‚ãƒ‡ã‚£ãƒ¼ãƒ—ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°ãƒ‡ã‚£ãƒ¼ãƒ—ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°ã€‚ãªã«ãã‚Œç¾Žå‘³ã„ã®ï¼Ÿ ã£ã¦æ„Ÿã˜ã ã‘ã©ã€ 2015å¹´æœ«ã« Google ãŒæ›¸ã„ãŸ ã€ŒMachine Learning with Financial Time Series Data on Google Clo
dai_yamashita 2016/05/31
machine learning
ãƒªãƒ³ã‚¯
https://jp.techcrunch.com/2016/01/26/20160125microsoft-moves-its-cntk-machine-learning-toolkit-to-github/
dai_yamashita 2016/01/26
machine learning

microsoft

deeplearning
ãƒªãƒ³ã‚¯
ç«¶é¦¬ã®äºˆæ¸¬ã‚’ã‚¬ãƒã§ã‚„ã£ã¦ã¿ãŸ - stockedge.jpã®æŠ€è¡“ãƒ¡ãƒ¢
åŸºæœ¬çš„ã«ç«¶é¦¬ãªã‚“ã¦ã‚„ã‚‹ã¹ãã§ã¯ãªã„ã¨ç§ã¯æ€ã£ã¦ã„ã‚‹ã€‚èƒ´å…ƒã®å–ã‚Šåˆ†ãŒå¤šã„ã‹ã‚‰ã ã€‚å®ãã˜ã«æ¯”ã¹ã‚Œã°ã¾ã ã¾ã—ã ãŒã€ãã‚Œã§ã‚‚è³ã‘é‡‘ã®20ï½ž30%ã¯èƒ´å…ƒã«å–ã‚‰ã‚Œã‚‹ã“ã¨ã«ãªã‚‹ã€‚*1 ã—ã‹ã—ä»Šå›žã¯ã€ã¡ã‚‡ã£ã¨æ€ã„ç«‹ã£ã¦ç«¶é¦¬ã®äºˆæ¸¬ã‚’ã‚„ã£ã¦ã¿ã‚‹ã“ã¨ã«ã—ãŸã€‚ ç†ç”±ã¯é¦¬åˆ¸ã®å®‰ã•ã ã€‚ç§ã¯ç¾åœ¨ã€è³‡é‡‘é‡ãŒå°‘ãªã„äººé–“ã§ã‚‚ä¸åˆ©ã«ãªã‚‰ãªã„æŠ•è³‡å…ˆã‚’æŽ¢ã—ã¦ã„ã‚‹ã®ã ãŒã€é¦¬åˆ¸ã®ä¸€æžš100å††ã¨ã„ã†å®‰ã•ã¯é…åŠ›çš„ã«æ˜ ã‚‹ã€‚æ ªã®å ´åˆã«ã¯ã©ã‚“ãªå®‰ã„æ ªã§ã‚ã‚Œæœ€ä½Žè³¼å…¥é¡ã¯æ•°ä¸‡å††ä»¥ä¸Š*2ãªã®ã§ã€ã‚ã‚‹ç¨‹åº¦ã¾ã¨ã¾ã£ãŸè³‡é‡‘ãŒå¿…è¦ã«ãªã‚‹ã€‚ ã¾ãŸã€ç«¶é¦¬ã«ã¯æŠ€è¡“ä»‹å…¥ã®ä½™åœ°ï¼ˆåŠªåŠ›æ¬¡ç¬¬ã§å‹åˆ©ã§ãã‚‹å¯èƒ½æ€§ï¼‰ãŒã‚ã‚‹ã€‚ ä¾‹ãˆã°ã“ã‚“ãªä¾‹ãŒã‚ã‚‹ã€‚ ï¼‘ï¼–ï¼å„„å††ãƒœãƒå„²ã‘ï¼è‹±æŠ•è³‡ä¼šç¤¾ãŒæ—¥æœ¬ã®ç«¶é¦¬ã§è’ç¨¼ãŽã—ãŸé©šãã®æ‰‹æ³• - NAVER ã¾ã¨ã‚ å½¼ã‚‰ã¯çµ±è¨ˆè§£æžã«ã‚ˆã£ã¦ç«¶é¦¬ã§å‹ã£ã¦ãŠã‚Šã€ãã®æ‰€å¾—ã‚’éš ã—ã¦ã„ãŸã‚‰ã—ã„ã€‚ã“ã†ã„ã†ãƒ‹ãƒ¥ãƒ¼ã‚¹ãŒå‡ºã‚‹ã¨ã„ã†ã“ã¨ã¯ã€è§£æžè€…ã®è…•æ¬¡ç¬¬ã§ã¯ç«¶é¦¬ã§å‹ã¦ã‚‹å¯èƒ½æ€§ãŒ
dai_yamashita 2016/01/04
ç«¶é¦¬

çµ±è¨ˆ

machine learning

R
ãƒªãƒ³ã‚¯
åºƒå‘Šã¨æ©Ÿæ¢°å¦ç¿’ - Qiita
Machine Learning Advent Calendarå‘ã‘ã®è¨˜äº‹ã§ã™ã€‚ æ™®æ®µã¯Gunosyã¨ã„ã†ä¼šç¤¾ã§ç¤¾é•·æ¥ã‚’ã—ãªãŒã‚‰ç¤¾é•·ã‚’ã—ã¦ã„ã¾ã™ã€‚ ã–ã£ãã‚Šã„ã†ã¨ çµè«–ã ã‘çŸ¥ã‚ŠãŸã„äººã¯ã“ã“ã ã‘ åºƒå‘Šã«ãŠã‘ã‚‹æ©Ÿæ¢°å¦ç¿’ã®å¿œç”¨ã®å¤šãã¯CTRäºˆæ¸¬ã‚„é‹ç”¨ã®æœ€é©åŒ–ã®ãŸã‚(ã‚¯ã‚¨ãƒªãƒ¼äºˆæ¸¬ã¨ã‹)ã®äºˆæ¸¬å•é¡Œ ä»Šå¾Œã¯ã€ŒCVRã®äºˆæ¸¬ã€ã‚„ã€Œã‚¢ã‚¯ãƒ†ã‚£ãƒ–ãªãƒ¦ãƒ¼ã‚¶ãƒ¼ã®äºˆæ¸¬ã€ãŒãƒ›ãƒƒãƒˆãªè©±é¡Œã«ãªã‚‹(åŠ ãˆã¦ãã®é‹ç”¨ã‚’ã©ã†æœ€é©åŒ–ã™ã‚‹ã‹ã¨ã„ã£ãŸè©±é¡Œã‚‚) ç¾åœ¨ã¯æ¤œç´¢ã‚¨ãƒ³ã‚¸ãƒ³ã®å¿œç”¨ä¾‹ãŒå¤šã„ã€‚ä»Šå¾Œã¯ãƒ‡ã‚£ã‚¹ãƒ—ãƒ¬ã‚¤åºƒå‘Šã‚„ã‚¿ã‚¤ãƒ ãƒ©ã‚¤ãƒ³åºƒå‘Šã¸ã®å¿œç”¨ãŒå¢—ãˆã¦ã„ã å€‹äººã®ãƒ¦ãƒ¼ã‚¶ãƒ¼å±žæ€§ã‚’é›†ã‚ã‚‹ã“ã¨ãŒä»Šã¾ã§ä»¥ä¸Šã«ãƒ¡ãƒ‡ã‚£ã‚¢ã®ãƒ“ã‚¸ãƒã‚¹çš„ã«é‡è¦ã«ãªã‚‹ åºƒå‘Šã‚„æŽ¨è–¦ã‚¨ãƒ³ã‚¸ãƒ³ã«é™ã‚‰ãšãƒ‰ãƒ¡ã‚¤ãƒ³çŸ¥è˜ã¯éžå¸¸ã«é‡è¦ã€‚ãƒ‰ãƒ¡ã‚¤ãƒ³çŸ¥è˜ã¨æ©Ÿæ¢°å¦ç¿’ã®çŸ¥è˜ã‚’æŒã£ãŸã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢ãŒæ„æ€æ±ºå®šã«æºã‚ã‚‹ä¼šç¤¾ã¯ä»Šå¾Œå¤§ããã®ã³ã‚‹(ã¨æ€ã†) åºƒå‘Šã«ã¤ã„ã¦ æœ€è¿‘ã¯ã‚‚ã£ã±ã‚‰åºƒå‘Šã®é–‹ç™ºã‚’ã—ã¦ãŠã‚Šã€åºƒå‘Šåˆ†é‡Žã§
dai_yamashita 2013/12/22
åºƒå‘Š

machine learning

æ©Ÿæ¢°å¦ç¿’

business
ãƒªãƒ³ã‚¯
Googleã®äººã®ã‚ªãƒ¼ã‚¯ã‚·ãƒ§ãƒ³ç†è«–è«–æ–‡ã§ã‚‚èªã‚“ã§ã¿ã‚‹ ãã®1 - Fire and Motion
Goel, G., Mirrokni, V. and Leme, R. P., Polyhedral Clinching Auctions and the Adwords Polytope, 44th ACM Symposium on Theory of Computing (STOC 2012). Google ã®2012å¹´excellent paperãŒæŒ™ã’ã‚‰ã‚Œã¦ã„ã¦ï¼Œãã®ä¸ã«ã‚ªãƒ¼ã‚¯ã‚·ãƒ§ãƒ³ç†è«–ã®è«–æ–‡ãŒã‚ã£ãŸï¼ŽMachine Learningã¨ç•°ãªã‚Šï¼Œã‚ªãƒ¼ã‚¯ã‚·ãƒ§ãƒ³ç†è«–ï¼Œãƒ¡ã‚«ãƒ‹ã‚ºãƒ ãƒ‡ã‚¶ã‚¤ãƒ³ã¯è‡ªåˆ†ã®å°‚é–€åˆ†é‡Žã®ä¸€ã¤ãªã®ã§ï¼Œã‹ã„ã¤ã¾ã‚“ã§ç´¹ä»‹ã—ã¦ã¿ã‚‹ï¼Žã‚ã¾ã‚ŠåŽ³å¯†ãªæ•°å¦çš„è¨˜è¿°ã¯è¡Œã‚ãšï¼Œã‚ã‹ã‚Šã‚„ã™ã•é‡è¦–ã§èª¬æ˜Žã—ã¦ã¿ãŸã„ï¼Ž ã¾ãšï¼Œã‚ªãƒ¼ã‚¯ã‚·ãƒ§ãƒ³ã«é–¢ã™ã‚‹å¤šãã®èª¤è§£ã‚’è§£ã„ã¦ãŠããŸã„ï¼Žã‚ªãƒ¼ã‚¯ã‚·ãƒ§ãƒ³ã¨ã„ã†ã¨ã‚ã‚‹å“ç‰©ï¼ˆè²¡ï¼‰ã‚’é«˜ãå£²ã‚Šã¤ã‘ã‚‹æ–¹æ³•ï¼Œã¾ãŸã¯ï¼ˆãƒ¤ãƒ•ã‚ªã‚¯ã®ã‚ˆã†ã«ï¼‰ã„ã‚‰ãªã„ã‚‚ã®ã‚’å‡¦åˆ†ã™ã‚‹æ–¹æ³•ã¨å®Ÿç”¨ä¸Šï¼Œæ‰ãˆã‚‰ã‚ŒãŒ
dai_yamashita 2013/06/24
google

auction

machine learning

ãƒ¡ã‚«ãƒ‹ã‚ºãƒ ãƒ‡ã‚¶ã‚¤ãƒ³

algorithm
ãƒªãƒ³ã‚¯
1