[B! machine-learning][chainer] tokuryooã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯

tokuryoo id:tokuryoo

machine-learningã¨chainerã«é–¢ã™ã‚‹tokuryooã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯ (7)

${{author_name}}$

{{{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}}

PTGHï¼šæ©Ÿæ¢°å¦ç¿’ãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ãƒãƒ¥ãƒ¼ãƒ‹ãƒ³ã‚°ã‚’Deep Learningã¨MCMCã§é«˜é€Ÿã«æœ€é©åŒ–ã™ã‚‹ãƒ•ãƒ¬ãƒ¼ãƒ ãƒ¯ãƒ¼ã‚¯ - æ¸‹è°·é§…å‰ã§åƒããƒ‡ãƒ¼ã‚¿ã‚µã‚¤ã‚¨ãƒ³ãƒ†ã‚£ã‚¹ãƒˆã®ãƒ–ãƒã‚°
è‹¦ç¯€2å¹´ã€ã¨ã†ã¨ã†å®Œæˆã—ã¾ã—ãŸã€‚æ©Ÿæ¢°å¦ç¿’ã®ãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ãƒãƒ¥ãƒ¼ãƒ‹ãƒ³ã‚°ã«æ‚©ã‚ã‚‹çš†ã•ã‚“ã®ãŸã‚ã«ã€ã‚³ãƒ¼ãƒ‡ã‚£ãƒ³ã‚°ã‚‚æ•°å¦ã‚‚å¤§ã®è‹¦æ‰‹ãªåƒ•ãŒé ‘å¼µã£ã¦ä½œã‚Šã¾ã—ãŸã€‚ãã‚ŒãŒPTGH (Parameter Tuning by God's Hand)ãƒ•ãƒ¬ãƒ¼ãƒ ãƒ¯ãƒ¼ã‚¯ã§ã™ã€‚Rã§ã‚‚Pythonã§ã‚‚å‹•ãã¾ã™ã€‚ ä¸èº«ã¨ã—ã¦ã¯ã€ä»£è¡¨çš„ãªæ©Ÿæ¢°å¦ç¿’ã§ã‚ã‚‹ãƒã‚¸ã‚¹ãƒ†ã‚£ãƒƒã‚¯å›žå¸°ãƒ»SVMï¼ˆç·šå½¢orã‚¬ã‚¦ã‚·ã‚¢ãƒ³ã‚«ãƒ¼ãƒãƒ«ï¼‰ãƒ»ãƒ©ãƒ³ãƒ€ãƒ ãƒ•ã‚©ãƒ¬ã‚¹ãƒˆãƒ»Xgboostãƒ»Deep NNãƒ»Convolutional NNã®ãã‚Œãžã‚Œã®ãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ãƒãƒ¥ãƒ¼ãƒ‹ãƒ³ã‚°ã‚’ã€arXivã«ä¸ŠãŒã£ã¦ã„ã‚‹è«–æ–‡ã«é »å‡ºã®ãƒ‘ã‚¿ãƒ¼ãƒ³ã«çµžã£ãŸä¸Šã§ãã®ãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿æ§‹æˆã‚’Rãªã‚‰{mxnet}ã§ã€Pythonãªã‚‰Chainer / TensorFlowã§å›žã™éš›ã®è¨˜æ³•ã«åˆã‚ã›ã¦Deep Learningã§å¦ç¿’ã•ã›ã€ãã®å¦ç¿’æ¸ˆã¿ãƒ¢ãƒ‡ãƒ«ã«åŸºã¥ã„ã¦MCMCã§æœ€é©ãªãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ã®çµ„ã¿åˆã‚ã›ã‚’é©å¿œçš„ã«æŽ¢ã—å‡ºã—ã¦æœ€é©
tokuryoo 2016/04/01
chainer

tensorflow

deep learning

machine-learning
ãƒªãƒ³ã‚¯
TensorFlowã®tutorialã‚’Chainerã§ã‚‚å®Ÿè£…ã—ã¦ã¿ãŸ - Qiita
# -*- coding: utf-8 -*- import input_data print 'load MNIST dataset' mnist = input_data.read_data_sets("MNIST_data", one_hot=True) import tensorflow as tf sess = tf.InteractiveSession() import time x = tf.placeholder("float", [None, 784]) y_ = tf.placeholder("float", [None, 10]) W = tf.Variable(tf.zeros([784, 10])) b = tf.Variable(tf.zeros([10])) # normal distribution def weight_variable(shape): i
tokuryoo 2015/11/13
deep learning

tensorflow

chainer

machine-learning
ãƒªãƒ³ã‚¯
Chainer - Qiita Advent Calendar 2015 - Qiita
Deep Learningãƒ•ãƒ¬ãƒ¼ãƒ ãƒ¯ãƒ¼ã‚¯Chainerã®Advent Calendarã§ã™ã€‚Chainerã«é–¢ã™ã‚‹æ§˜ã€…ãªè¨˜äº‹ã‚’å‹Ÿé›†ã—ã¦ã„ã¾ã™ã€‚ Chainerã‚’ä½¿ã£ã¦ã¿ãŸã€Chainerã¯ã“ã‚“ãªä½¿ã„æ–¹ã‚‚ã§ãã‚‹ Chainerã‚’ä½¿ã£ãŸã‚·ã‚¹ãƒ†ãƒ ãƒ»ã‚µãƒ¼ãƒ“ã‚¹ã‚’ä½œã£ãŸ Chainerã®ãƒ¢ã‚¸ãƒ¥ãƒ¼ãƒ«è§£èª¬ Chainerã«ã“ã†ã„ã†ãƒ¢ã‚¸ãƒ¥ãƒ¼ãƒ«ãƒ»æ©Ÿèƒ½ãŒã»ã—ã„ Advent Calendar on Deep Learning Framework Chainer. We call for articles about Chainer including but not limited to: I tried Chainer. I used Chainer in this way. I built a service or system with Chainer. I wrote a think piece of
tokuryoo 2015/11/13
chainer

deep learning

machine-learning
ãƒªãƒ³ã‚¯
Chainerã«ã‚ˆã‚‹å¤šå±¤ãƒ‘ãƒ¼ã‚»ãƒ—ãƒˆãƒãƒ³ã®å®Ÿè£… - äººå·¥çŸ¥èƒ½ã«é–¢ã™ã‚‹æ–å‰µéŒ²
ã“ã‚Œã¾ã§Deep Learningã®ã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ ã‚’Theanoã§å®Ÿè£…ã—ã¦ããŸï¼ˆ2015/4/29ï¼‰ã‘ã‚Œã©ã€ã“ã“ã‚‰ã§å··ã§å¤§äººæ°—ã®ãƒ©ã‚¤ãƒ–ãƒ©ãƒªChainerã«ã‚‚æ‰‹ã‚’å‡ºã—ã¦ã¿ãŸã€‚Theanoã®å‹‰å¼·ã‚’å§‹ã‚ãŸã‚ã¨ã™ãã«ChainerãŒå…¬é–‹ã•ã‚ŒãŸï¼ˆ2015/6/9ï¼‰ãŒãƒ¦ãƒ¼ã‚¶ã‚„æƒ…å ±ãŒå¢—ãˆã‚‹ã¾ã§å¾…ã£ã¦ã„ãŸæ„Ÿã˜ï¼ˆç¬‘ï¼‰æœ€è¿‘ã¯ã‚³ãƒ¼ãƒ‰ã‚„å®Ÿé¨“çµæžœãªã©ã‚’å…¬é–‹ã—ã¦ãã‚Œã‚‹äººãŒå¢—ãˆã¦ããŸã®ã§éžå¸¸ã«å‚è€ƒã«ãªã£ã¦ã„ã‚‹ã€‚ç›®ã«ã¤ã„ãŸã‚‚ã®ã¯ã¦ã¶ã«ç™»éŒ²ã—ã¦ã„ã‚‹ã®ã§ã€èˆˆå‘³ã‚’æŒã£ãŸæ‰‹æ³•ã¯ãŒã—ãŒã—å‹‰å¼·ã—ã¦è¿½è©¦ã—ã¦ã„ããŸã„ã€‚ Chainerã®ãƒãƒ¼ã‚¸ãƒ§ãƒ³ã¯1.3.2ã‚’ãƒ™ãƒ¼ã‚¹ã«ã—ã¦ã„ã‚‹ã€‚1.3ã‹ã‚‰PyCUDA/scikit-cudaã‚’ç‹¬è‡ªãƒ©ã‚¤ãƒ–ãƒ©ãƒªã®CuPyã«ç½®ãæ›ãˆãŸã¨ã®ã“ã¨ã§ã€ä»¥å‰ã®ã‚³ãƒ¼ãƒ‰ã¯å°‘ã—ä¿®æ£ã—ãªã„ã¨å‹•ã‹ãªã„ã‚ˆã†ã ã€‚ãã®åˆ†ã€1.3ã‹ã‚‰ã¯ã‚¤ãƒ³ã‚¹ãƒˆãƒ¼ãƒ«ãŒã‚·ãƒ³ãƒ—ãƒ«ã«ãªã£ã¦ã„ã¦ã¨ã¦ã‚‚ã†ã‚Œã—ã„ã€‚1.1ã®ã“ã‚ã¯ã€Chainerã¨ç›´æŽ¥é–¢ä¿‚ãªã„PyCUD
tokuryoo 2015/10/06
chainer

machine-learning

deep learning
ãƒªãƒ³ã‚¯
æ©Ÿæ¢°å¦ç¿’ãƒ©ã‚¤ãƒ–ãƒ©ãƒª Chainerã®ç´¹ä»‹ - ã®ã‚“ã³ã‚Šã—ã¦ã„ã‚‹ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢ã®æ—¥è¨˜
çš†ã•ã‚“ã“ã‚“ã«ã¡ã¯ ãŠå…ƒæ°—ã§ã™ã‹ã€‚ç§ã¯å…ƒæ°—ã§ã™ã€‚ Chainerã¨å‘¼ã°ã‚Œã‚‹æ©Ÿæ¢°å¦ç¿’ãƒ©ã‚¤ãƒ–ãƒ©ãƒªã‚’ç´¹ä»‹ã—ã‚ˆã†ã¨æ€ã„ã¾ã™ã€‚ Chainerã«ã¤ã„ã¦ Chainerã¨ã¯ï¼Ÿ Chainerã¯Preffered NetworksãŒé–‹ç™ºã—ãŸãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã‚’èª¤å·®ä¼æ’ã§å¦ç¿’ã™ã‚‹ ãƒ©ã‚¤ãƒ–ãƒ©ãƒªã§ã™ã€‚(Python)chainer.org ç‰¹å¾´ã¨ã—ã¦ã€Chainer ã¯ã€ã€Œå®Ÿéš›ã« Python ã®ã‚³ãƒ¼ãƒ‰ã‚’ç”¨ã„ã¦å…¥åŠ›é…åˆ—ã«ä½•ã®å‡¦ç†ãŒé©ç”¨ã•ã‚ŒãŸã‹ã ã‘ã‚’è¨˜æ†¶ã—ã¦ãŠãã€ãã‚Œã‚’èª¤å·®é€†ä¼æ’ã®å®Ÿè¡Œã«ä½¿ã„ã¾ã™ã€ã ãã†ã€‚ Install sudo pip install chainer åŸºæœ¬çš„ã«ã“ã‚Œã ã‘ã®ã‚¤ãƒ³ã‚¹ãƒˆãƒ¼ãƒ«ãŒéžå¸¸ã«ç°¡å˜ãªã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢ã§ã™ã€‚ ä»–ã®ãƒ©ã‚¤ãƒ–ãƒ©ãƒªã¨ã®æ¯”è¼ƒ ãƒ‡ã‚£ãƒ¼ãƒ—ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°ãŒæ´»ã‹ã™IoTã‚ˆã‚ŠæŠœç²‹ã€‚ å€‹äººçš„ã«æ³¨ç›®ã—ãŸé•ã„ã¯ä»¥ä¸‹ã®3ç‚¹ Caffeã‚‚Theanoã‚‚å‹‰å¼·ã™ã‚‹ã“ã¨ãŒå¤šã„ã€‚ï¼ˆè¨å®šãƒ•ã‚¡ã‚¤ãƒ«ã¨ã‹ï¼‰ çŸãæ›¸ã‘
tokuryoo 2015/09/28
chainer

machine-learning
ãƒªãƒ³ã‚¯
Chainer: A flexible framework for neural networks
A Powerful, Flexible, and Intuitive Framework for Neural Networks Get Started Learn More
tokuryoo 2015/06/21
machine-learning

chainer

deep learning
ãƒªãƒ³ã‚¯
åˆ†æ•£æ·±å±¤å¼·åŒ–å¦ç¿’ã§ãƒãƒœãƒƒãƒˆåˆ¶å¾¡ - Preferred Networks Research & Development
æ–°å…¥ç¤¾å“¡ã®æ¾å…ƒã§ã™ã€‚ã¯ã˜ã‚ã¾ã—ã¦ã€‚ â€œåˆ†æ•£æ·±å±¤å¼·åŒ–å¦ç¿’â€ã®æŠ€è¡“ãƒ‡ãƒ¢ã‚’ä½œæˆã—ã€å…¬é–‹ã„ãŸã—ã¾ã—ãŸã€‚ãƒãƒœãƒƒãƒˆã‚«ãƒ¼ãŒ0ã‹ã‚‰å‹•ä½œã‚’å¦ç¿’ã—ã¦ã„ãã¾ã™ï¼ ã¾ãšã¯ã“ã®å‹•ç”»ã‚’å¾¡è¦§ãã ã•ã„ã€‚ ä»¥ä¸‹ã§ã€å‹•ç”»ã®è¦‹ã©ã“ã‚ã¨ã€ä½¿ã£ã¦ã„ã‚‹æŠ€è¡“ã‚’ç´¹ä»‹ã—ã¾ã™ã€‚ å‹•ç”»ã®è¦‹ã©ã“ã‚ Car 0(â—‹ã®ä»˜ã„ã¦ã„ã‚‹è»Š)ãŒå³æŠ˜ã‚«ãƒ¼ãƒ–ã®æ‰‹å‰ã§æ¸›é€Ÿã™ã‚‹æ§˜å(å³ç”»é¢ã®ç™½ã„ãƒãƒ¼ã®ã¨ã“ã‚ãŒã€ãƒ–ãƒ¬ãƒ¼ã‚ã®ã¨ã“ã‚ã§èµ¤ããªã£ã¦ã„ã‚‹ã€‚ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆã¯ãƒ–ãƒ¬ãƒ¼ã‚ãŒæœ€ã‚‚å¤šãå ±é…¬ãŒå¾—ã‚‰ã‚Œã‚‹ã¨æŽ¨æ¸¬ã—ã¦ã„ã‚‹ã“ã¨ãŒã‚ã‹ã‚‹)ã€‚é€Ÿã„é€Ÿåº¦ã»ã©å ±é…¬ã¯å¤§ãã„ãŒã€ã‚«ãƒ¼ãƒ–ã‚’æ›²ãŒã‚Šãã‚Œãšå£ã«ã¶ã¤ã‹ã£ã¦ã—ã¾ã†ã®ã§å¦ç¿’ãŒé€²ã‚€ã¨ã‚«ãƒ¼ãƒ–æ‰‹å‰ã§ã®ã¿æ¸›é€Ÿã™ã‚‹ã‚ˆã†ã«ãªã‚‹ã€‚ ç›®ã®å‰ã«è»ŠãŒã„ã‚‹ã¨ãã¯ä¸€æ™‚åœæ¢ã—ã¦ã€ã„ãªããªã£ã¦ã‹ã‚‰åŠ é€Ÿã™ã‚‹ã€‚ ã‚¨ãƒã‚ªãƒ”ã‚¢ã«ã¯æœ¬å½“ã«ã“ã®ã‚ˆã†ãªäº¤å·®ç‚¹ãŒã‚ã‚‹ã‚‰ã—ã„ã€‚ ãŽã‚ŠãŽã‚Šã§ã™ã‚Œé•ã†2å°ã€‚å¦ç¿’é€”ä¸ã§ã¯ã™ã‚Œé•ã„ãã‚Œãšã«ã¶ã¤ã‹ã£ã¦å€’ã‚Œã¦ã—ã¾ã†ã“ã¨ã‚‚ã‚ã‚‹(æ—©é€ã‚Šã‚·ãƒ¼ãƒ³ä¸ã«äººãŒå†™ã£ã¦
tokuryoo 2015/06/11
machine-learning

deep learning
ãƒªãƒ³ã‚¯
1