[B! machinelearning] tomo_thumbã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯

tomo_thumb id:tomo_thumb

machinelearningã«é–¢ã™ã‚‹tomo_thumbã®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}}

æœ€è¿‘ã®ã‚¹ãƒ‘ãƒ¼ã‚¹ãªãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã«ã¤ã„ã¦ - SmartNews Engineering Blog
ã“ã‚“ã«ã¡ã¯ã€ã‚¹ãƒžãƒ¼ãƒˆãƒ‹ãƒ¥ãƒ¼ã‚¹ã®å¾³æ°¸ã§ã™ã€‚æ·±å±¤å¦ç¿’æ¥ç•Œã¯GANã ã¨ã‹æ·±å±¤å¼·åŒ–å¦ç¿’ã ã¨ã‹ã§ç››ã‚Šä¸ŠãŒã£ã¦ã„ã¾ã™ãŒã€ä»Šæ—¥ã¯æ·¡ã€…ã¨ã€ã‚¹ãƒ‘ãƒ¼ã‚¹ãªãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã®è©±ã‚’ã—ã¾ã™ã€‚ è¦ç´„ã™ã‚‹ã¨ ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆã®ã‚¹ãƒ‘ãƒ¼ã‚¹åŒ–ã«ã‚ˆã£ã¦ã€ç²¾åº¦ã¯ã»ã¨ã‚“ã©çŠ ç‰²ã«ã›ãšã«ã€è¨ˆç®—åŠ¹çŽ‡ã¯3ã€œ5å€ç¨‹åº¦ã¾ã§å‘ä¸Šã§ãã‚‹ ã‚¹ãƒ‘ãƒ¼ã‚¹åŒ–ã«ã¯ã¾ã èª²é¡ŒãŒå¤šãã€ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆã®é«˜é€ŸåŒ–ã¨ã„ã†æ„å‘³ã§ã¯ã€æ¬¡ã®æˆ¦å ´ã¯ãŸã¶ã‚“ã“ã“ã«ãªã‚‹ ã‚¹ãƒ‘ãƒ¼ã‚¹ã¨ã¯ã€ã‚¹ãƒ‘ãƒ¼ã‚¹åŒ–ã¨ã¯ ã‚¹ãƒ‘ãƒ¼ã‚¹ã§ã‚ã‚‹ã¨ã¯ã€å€¤ã®ã»ã¨ã‚“ã©ãŒ0ã§ã‚ã‚‹ã“ã¨ã§ã™ã€‚ä¾‹ãˆã°ã€ãƒ™ã‚¯ãƒˆãƒ«$a,b$ã®å†…ç©ã‚’è¨ˆç®—ã™ã‚‹éš›ã«ã€$a$ã®ã»ã¨ã‚“ã©ã®è¦ç´ ã®å€¤ãŒ0ã§ã‚ã‚‹ã¨ã—ã¾ã—ã‚‡ã†ã€‚0ã«ãªã«ã‚’ã‹ã‘ã¦ã‚‚0ã§ã™ã‹ã‚‰ã€$a$ã®å€¤ãŒ0ã§ãªã„æ¬¡å…ƒã«ã¤ã„ã¦ã®ã¿ã€$a_i b_i$ã®å€¤ã‚’è¨ˆç®—ã—ã¦è¶³ã—åˆã‚ã›ã‚Œã°ã‚ˆã„ã‚ã‘ã§ã™ã€‚ã“ã®ã‚ˆã†ã«ã€å†…ç©ã‚’è¨ˆç®—ã™ã‚‹éš›ã«ã€ã©ã¡ã‚‰ã‹ã®ãƒ™ã‚¯ãƒˆãƒ«ãŒã‚¹ãƒ‘ãƒ¼ã‚¹ã§ã‚ã‚Œã°è¨ˆç®—ãŒé«˜é€ŸåŒ–ã§ãã¾ã™ã€‚0ã¨ã„ã†å€¤ã‚’ãƒ¡ãƒ¢ãƒª
tomo_thumb 2017/06/26
machinelearning
ãƒªãƒ³ã‚¯
Theanoã«ã‚ˆã‚‹å¤šå±¤ãƒ‘ãƒ¼ã‚»ãƒ—ãƒˆãƒãƒ³ã®å®Ÿè£… - äººå·¥çŸ¥èƒ½ã«é–¢ã™ã‚‹æ–å‰µéŒ²
Theanoã«ã‚ˆã‚‹ãƒã‚¸ã‚¹ãƒ†ã‚£ãƒƒã‚¯å›žå¸°ã®å®Ÿè£…ï¼ˆ2015/5/26ï¼‰ã®ã¤ã¥ãã€‚ä»Šå›žã¯ã€Deep Learning Tutorialã®å¤šå±¤ãƒ‘ãƒ¼ã‚»ãƒ—ãƒˆãƒãƒ³ï¼ˆMultilayer Perceptronï¼‰ã‚’å®Ÿè£…ã—ã¦ã¿ã‚‹ã€‚ã‚¿ã‚¹ã‚¯ã¯å‰å›žã¨åŒã˜MNISTã®æ‰‹æ›¸ãæ•°å—èªè˜ã€‚å¤šå±¤ãƒ‘ãƒ¼ã‚»ãƒ—ãƒˆãƒãƒ³ã¯ã“ã‚Œã¾ã§ã‚‚ä½•å›žã‹å®Ÿè£…ã—ã¦ããŸï¼ˆ2010/8/29ï¼‰ã‘ã©ä»Šå›žã¯Theanoã‚’ä½¿ã£ã¦ã¿ã‚ˆã†ã¨ã„ã†è¶£æ—¨ã€‚ã“ã‚Œã¾ã§ã‚ˆã‚Šãšã„ã¶ã‚“ç°¡å˜ã«å®Ÿè£…ã§ãã‚‹ã“ã¨ãŒã‚ã‹ã‚‹ã€‚ ã‚½ãƒ¼ã‚¹ã‚³ãƒ¼ãƒ‰å…¨ä½“ã¯ã“ã“ã«ç½®ã„ãŸã€‚ å¤šå±¤ãƒ‘ãƒ¼ã‚»ãƒ—ãƒˆãƒãƒ³ ä¸Šã®å›³ã¯å…¥åŠ›å±¤ã€éš ã‚Œå±¤ã€å‡ºåŠ›å±¤3å±¤ãƒ‘ãƒ¼ã‚»ãƒ—ãƒˆãƒãƒ³ã®æ¨¡å¼å›³ã€‚å…¥åŠ›å±¤ã«å…¥åŠ›ã•ã‚ŒãŸãƒ™ã‚¯ãƒˆãƒ«ã¯ã€å…¥åŠ›å±¤ã¨éš ã‚Œå±¤é–“ã®é‡ã¿è¡Œåˆ— ã¨ãƒã‚¤ã‚¢ã‚¹ãƒ™ã‚¯ãƒˆãƒ« ã«ã‚ˆã£ã¦ ã§å¤‰æ›ã•ã‚Œã€éš ã‚Œå±¤ã®å‡ºåŠ›ã¨ãªã‚‹ã€‚æ´»æ€§åŒ–é–¢æ•°ã¨ã—ã¦ä½¿ã‚ã‚Œã‚‹ãƒã‚¸ã‚¹ãƒ†ã‚£ãƒƒã‚¯ãƒ»ã‚·ã‚°ãƒ¢ã‚¤ãƒ‰é–¢æ•° sigmoid ã«ã‚ˆã£ã¦å…¥åŠ›ãƒ™ã‚¯ãƒˆãƒ«ã¯éžç·šå½¢å¤‰æ›ã•ã‚Œã‚‹ã€‚ã¤ã¾ã‚Šã‚‚ã¨ã®ç©ºé–“ã§ç·šå½¢åˆ†é›¢ä¸å¯èƒ½
tomo_thumb 2017/06/21
deep learning

deeplearning

machinelearning
ãƒªãƒ³ã‚¯
Machine Learning | Coursera
We asked all learners to give feedback on our instructors based on the quality of their teaching style.
tomo_thumb 2017/03/25
machinelearning
ãƒªãƒ³ã‚¯
ã€æ±ºå®šç‰ˆã€‘Macã§Pythonã‚’ä½¿ã£ã¦ã€Žæ©Ÿæ¢°å¦ç¿’ã€ã‚’å¦ã¶ãŸã‚ã®ç’°å¢ƒæ§‹ç¯‰ - Qiita
æ ªå¼ä¼šç¤¾ã‚ã‚«ã‚¬ã‚¯ æ©Ÿæ¢°å¦ç¿’ã‚„äººå·¥çŸ¥èƒ½ã®æ•™è‚²ã‚µãƒ¼ãƒ“ã‚¹ã‚’æä¾› ãƒ•ã‚©ãƒãƒ¼ãŠå¾…ã¡ã—ã¦ãŠã‚Šã¾ã™ ãƒ“ã‚¸ãƒã‚¹ç›®ç·šã®æ©Ÿæ¢°å¦ç¿’ãƒ»äººå·¥çŸ¥èƒ½ã®æƒ…å ±ã‚„ã‚ªã‚¹ã‚¹ãƒ¡ã®å‚è€ƒæ›¸ã«ã¤ã„ã¦ç™ºä¿¡ã—ã¦ã„ã¾ã™ã€‚ ä»£è¡¨å–ç· å½¹ç¤¾é•·ã€€å‰å´Ž äº®ä»‹ Twitterï¼š@yoshizaki_kkgk Facebookï¼š@ryosuke.yoshizaki Blogï¼šã‚ã‚«ã‚¬ã‚¯ä»£è¡¨ã®ãƒ–ãƒã‚° ãã‚Œã§ã¯ã€å‰ç½®ããŒé•·ããªã‚Šã¾ã—ãŸãŒã€ç’°å¢ƒæ§‹ç¯‰ã‚’ã¯ã˜ã‚ã¦ã„ãã¾ã—ã‚‡ã†ï¼ ãƒãƒ¼ã‚«ãƒ«ç’°å¢ƒï¼ˆMacï¼‰ ç’°å¢ƒã®é•ã„ã«ã‚ˆã‚Šã€è¨å®šãŒã†ã¾ãã„ãå ´åˆãŒã‚ã‚Šã¾ã™ã€‚ ç¾åœ¨ã€ç§ã®æ‰‹å…ƒã®PCã¯Macã®æœ€æ–°ç‰ˆOSãŒå…¥ã£ã¦ã„ã¾ã™ã€‚ ãƒ»macOS Sierra 10.12.3 ã†ã¾ãã„ã‹ãªã„å ´åˆã¯ã“ã¡ã‚‰ã«åˆã‚ã›ã¦ã¿ã¦ãã ã•ã„ã€‚ Homebrewã®ã‚¤ãƒ³ã‚¹ãƒˆãƒ¼ãƒ« Homebrewã¨ã„ã†ãƒ‘ãƒƒã‚±ãƒ¼ã‚¸ãƒžãƒãƒ¼ã‚¸ãƒ£ãƒ¼ã‚’å°Žå…¥ã—ã¾ã™ã€‚ æ—¥é ƒãƒ—ãƒã‚°ãƒ©ãƒŸãƒ³ã‚°ã‚’ã—ãªã„æ–¹ã¯èžãæ…£ã‚Œãªã„ã‹ã‚‚ã—ã‚Œã¾ã›ã‚“ãŒã€ãƒ—ãƒã‚°ãƒ©ãƒŸãƒ³ã‚°ã®
tomo_thumb 2017/03/25
machinelearning

deeplearning
ãƒªãƒ³ã‚¯
Image-to-Image Demo - Affine Layer
Recently, I made a Tensorflow port of pix2pix by Isola et al., covered in the article Image-to-Image Translation in Tensorflow. I've taken a few pre-trained models and made an interactive web thing for trying them out. Chrome is recommended. The pix2pix model works by training on pairs of images such as building facade labels to building facades, and then attempts to generate the corresponding out
tomo_thumb 2017/02/22
tensorflow

deep learning

deeplearning

machinelearning
ãƒªãƒ³ã‚¯
ãƒ‡ã‚£ãƒ¼ãƒ—ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°ï¼ˆTensorFlowï¼‰ã‚’ä½¿ç”¨ã—ãŸæ ªä¾¡äºˆæƒ³ ï½žãã®2ï½ž - Qiita
å‰å›žã®ç¶šãã€‚ ãƒ‡ã‚£ãƒ¼ãƒ—ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°ã®ãƒ•ãƒ¬ãƒ¼ãƒ ãƒ¯ãƒ¼ã‚¯ã§ã‚ã‚‹TensorFlowã‚’ä½¿ç”¨ã—ã¦æ ªä¾¡ã‚’äºˆæƒ³ã™ã‚‹ãžï½žã€ã¨ã„ã†ãŠè©±ã§ã™ã€‚ã¡ãªã¿ã«å‰å›žã¯å®Œå…¨ã«å¤±æ•—ã§ã—ãŸã€‚ å‰å›žã®ã‚³ãƒ¡ãƒ³ãƒˆã§ã€tawagoã•ã‚“ã‹ã‚‰ã€ŒGoogleãŒåŒã˜ã‚ˆã†ãªã“ã¨ã—ã¦ã„ã‚‹ã€ã¨ã„ã†æƒ…å ±ã‚’ã„ãŸã ã„ãŸã®ã§ã€ãã¡ã‚‰ã‚’ã‚³ãƒ”ãƒ»ãƒ»ãƒ»ã‚¤ãƒ³ã‚¹ãƒ‘ã‚¤ã‚¢ã—ã¦ã¿ã¾ã—ãŸã€‚ ##å‰å›žã¨ã®ç›¸é•ç‚¹ å‰å›žã¯ã€ã€Œæ•°æ—¥åˆ†ã®æ—¥çµŒå¹³å‡ã‚’ä½¿ç”¨ã—ã¦ã€æ¬¡ã®æ—¥ã®æ—¥çµŒå¹³å‡ãŒä¸ŠãŒã‚‹ã‹ã€ä¸‹ãŒã‚‹ã‹ã€å¤‰ã‚ã‚‰ãªã„ã‹ï¼ˆ3æŠžï¼‰ã‚’äºˆæƒ³ã™ã‚‹ã€ã‚‚ã®ã§ã—ãŸã€‚ Googleã®ãƒ‡ãƒ¢ã§ã¯ã€ã€Œæ•°æ—¥åˆ†ã®ä¸–ç•Œä¸ã®æ ªä¾¡æŒ‡æ•°ï¼ˆãƒ€ã‚¦ã€æ—¥çµŒå¹³å‡ã€FTSE100ã€DAXãªã©ï¼‰ã‚’ä½¿ç”¨ã—ã¦ã€æ¬¡ã®æ—¥ã®S&PãŒä¸ŠãŒã‚‹ã‹ä¸‹ãŒã‚‹ã‹ï¼ˆ2æŠžï¼‰ã‚’äºˆæƒ³ã™ã‚‹ã€ã¨ã„ã†å†…å®¹ã§ã—ãŸã€‚ ã¨ã„ã†ã“ã¨ã§ã€ä¸‹è¨˜ãŒå‰å›žã‹ã‚‰ã®ä¸»ãªå¤‰æ›´ç‚¹ã¨ãªã‚Šã¾ã™ã€‚ ã€Œä¸ŠãŒã‚‹ã‹ã€ã€Œä¸‹ãŒã‚‹ã‹ã€ã®2æŠž æ—¥çµŒå¹³å‡ã ã‘ã§ãªãã€ä»–å›½ã®æ ªä¾¡æŒ‡æ•°ã‚‚ä½¿ç”¨ éš ã‚Œå±¤x2ã€ãƒ¦ãƒ‹ãƒƒãƒˆæ•°ã¯50,25 äºˆæƒ³ã™ã‚‹
tomo_thumb 2016/04/10
deeplearning

machinelearning
ãƒªãƒ³ã‚¯
æ–‡ç³»ã§ã‚‚æ©Ÿæ¢°å¦ç¿’ãŒã‚ã‹ã‚‹ã‚ˆã†ã«ãªã‚‹æ•™ç§‘æ›¸ - EchizenBlog-Zwei
ç¤¾å†…ã®æœ‰å¿—ã§æ©Ÿæ¢°å¦ç¿’ã‚„æ•°å¦ã®å‹‰å¼·ä¼šã‚’ã„ãã¤ã‹ã‚„ã£ã¦ã„ã¾ã™ï¼ˆç§ä»¥å¤–ã®æ–¹ãŒä¸»å‚¬ã—ã¦ã„ã‚‹ã‚‚ã®ã‚‚ã‚ã‚‹ï¼‰ã€‚ã¨ãã«ç†ç³»ã§ã¯ãªã„æ–¹ã‚‚å‚åŠ ã•ã‚Œã¦ã„ã¾ã™ãŒã€ãã¡ã‚“ã¨é ‘å¼µã‚Œã°ã ã‚“ã ã‚“æ©Ÿæ¢°å¦ç¿’ãŒã§ãã‚‹ã‚ˆã†ã«ãªã‚‹ã¨ã„ã†ã“ã¨ãŒã‚ã‹ã£ã¦ããŸã®ã§ãƒ¡ãƒ¢ã—ã¦ãŠãã¾ã™ã€‚ ãªãŠã€æ©Ÿæ¢°å¦ç¿’ã‚’ã¨ã‚Šã‚ãˆãšå®Ÿè£…ã™ã‚‹ã ã‘ã ã£ãŸã‚‰ã‚‚ã£ã¨ç°¡å˜ã«å¦ã¶æ–¹æ³•ã‚‚ã„ã‚ã„ã‚ã‚ã‚Šã€ä»Šå›žã¯ã‚ãã¾ã§æ£æ”»æ³•ã§æ©Ÿæ¢°å¦ç¿’ã‚’å‹‰å¼·ã™ã‚‹ã€ã¨ã„ã†è¦³ç‚¹ã§ã®æ›¸ç±ã®é¸æŠžã¨ãªã£ã¦ã„ã¾ã™ã€‚æ€¥ãŒã°å›žã‚Œã¨ã„ã†è¨€è‘‰ã‚‚ã‚ã‚‹ã‚ˆã†ã«ã€ç„¦ã£ã¦æˆæžœã‚’æ±‚ã‚ãªã„ã®ã§ã‚ã‚Œã°åœ°é“ã«é ‘å¼µã‚‹ã»ã†ãŒå¾Œã€…å¿œç”¨ãŒåŠ¹ã„ã¦è‰¯ã„ã¨ã„ã†ã“ã¨ã‚‚ã‚ã‚Šã¾ã™ã€‚ é«˜å°‚ã®æ•°å¦ ãŠãã‚‰ãæ•°å¦ãŒã§ããªã„ã¨ã„ã†æ–¹ã¯é«˜æ ¡ã®æ•°å¦ã‚ãŸã‚Šã‹ã‚‰ç†è§£ãŒæ€ªã—ã„ã“ã¨ã«ãªã£ã¦ã„ã‚‹ã¨æ€ã„ã¾ã™ã€‚ã€Œé«˜å°‚ã®æ•°å¦ã€ã¯ä¸å¦æ•°å¦ã¾ã§ã®å‰æçŸ¥è˜ã§èªã‚ã‚‹æ•™ç§‘æ›¸ã§ã€ã‚ã‹ã‚Šã‚„ã™ã„ä¾‹é¡Œã‚„ç†è§£ã®åŠ©ã‘ã«ãªã‚‹ç·´ç¿’å•é¡ŒãŒå¤šæ•°ç”¨æ„ã•ã‚Œã¦ã„ã‚‹ãŸã‚ã€ãã¡ã‚“ã¨å•é¡Œã‚’è§£ã„ã¦ã„ã‘ã°ç„¡ç†ãªãé«˜å°‚ã®æ•°å¦(
tomo_thumb 2015/11/16
machinelearning
ãƒªãƒ³ã‚¯
æ©Ÿæ¢°å¦ç¿’ã«ã‚ˆã‚‹ãƒ‡ãƒ¼ã‚¿åˆ†æž å®Ÿè·µç·¨
æ¼”ç¿’ç”¨ã®ã‚¹ã‚¯ãƒªãƒ—ãƒˆã¯ä»¥ä¸‹ã«ã‚ã‚Šã¾ã™ï¼Ž Python http://nbviewer.ipython.org/gist/canard0328/a5911ee5b4bf1a07fbcb/ https://gist.github.com/canard0328/07a65584c134a2700725 R http://nbviewer.ipython.org/gist/canard0328/6f44229365f53b7bd30f/ https://gist.github.com/canard0328/b2f8aec2b9c286f53400 Read less
tomo_thumb 2015/11/01
machinelearning
ãƒªãƒ³ã‚¯
1