[B! development][deeplearning] chess-newsã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯

chess-news id:chess-news

developmentã¨deeplearningã«é–¢ã™ã‚‹chess-newsã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯ (12)

${{author_name}}$

{{{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}}

Home â€” TensorFlow
TensorFlow ã‚’ä½¿ç”¨ã™ã‚‹ã¨ã€ã‚ã‚‰ã‚†ã‚‹ç’°å¢ƒã§å®Ÿè¡Œã§ãã‚‹ ML ãƒ¢ãƒ‡ãƒ«ã‚’ç°¡å˜ã«ä½œæˆã§ãã¾ã™ã€‚ ã‚¤ãƒ³ã‚¿ãƒ©ã‚¯ãƒ†ã‚£ãƒ–ãªã‚³ãƒ¼ãƒ‰ã‚µãƒ³ãƒ—ãƒ«ã‚’ä½¿ç”¨ã—ã¦ã€ç›´æ„Ÿçš„ãª API ã®ä½¿ç”¨æ–¹æ³•ã‚’å¦ç¿’ã—ã¾ã—ã‚‡ã†ã€‚ import tensorflow as tf mnist = tf.keras.datasets.mnist (x_train, y_train),(x_test, y_test) = mnist.load_data() x_train, x_test = x_train / 255.0, x_test / 255.0 model = tf.keras.models.Sequential([ tf.keras.layers.Flatten(input_shape=(28, 28)), tf.keras.layers.Dense(128, activation='relu'), tf.keras.lay
chess-news 2019/10/15
ã€€æ—¥æœ¬èªž

tensorflow

development

deeplearning
ãƒªãƒ³ã‚¯
Deep Learning JP
æ¾å°¾ãƒ»å²©æ¾¤ç ”ç©¶å®¤ä¸»å‚¬ã®å…¬é–‹è¬›åº§ã€Œå¤§è¦æ¨¡è¨€èªžãƒ¢ãƒ‡ãƒ« 2024ã€ã‚’é–‹è¬›ã—ã¾ã™. å—è¬›ã‚’å¸Œæœ›ã•ã‚Œã‚‹æ–¹ã¯ä¸‹è¨˜ãƒšãƒ¼ã‚¸ã‚’å‚è€ƒã«ã—ã¦ãã ã•ã„. å¤§è¦æ¨¡è¨€èªžãƒ¢ãƒ‡ãƒ« 2024 ç”³è¾¼ç· åˆ‡â”‚ more
chess-news 2018/07/07
AI

deeplearning

deep learning

äººå·¥çŸ¥èƒ½

research

development

workshop

æ©Ÿæ¢°å¦ç¿’

ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆ
ãƒªãƒ³ã‚¯
Applying deep learning to real-world problems
The rise of artificial intelligence in recent years is grounded in the success of deep learning. Three major drivers caused the breakthrough of (deep) neural networks: the availability of huge amounts of training data, powerful computational infrastructure, and advances in academia. Thereby deep learning systems start to outperform not only classical methods, but also human benchmarks in various t
chess-news 2017/05/29
deep learning

DeepLearning

Development

ai
ãƒªãƒ³ã‚¯
Torch | Scientific computing for LuaJIT.
What is Torch? Torch is a scientific computing framework with wide support for machine learning algorithms that puts GPUs first. It is easy to use and efficient, thanks to an easy and fast scripting language, LuaJIT, and an underlying C/CUDA implementation. A summary of core features: a powerful N-dimensional array lots of routines for indexing, slicing, transposing, â€¦ amazing interface to C, via
chess-news 2017/05/27
development

deeplearning

æ©Ÿæ¢°å¦ç¿’

deep learning
ãƒªãƒ³ã‚¯
Open-sourcing DeepMind Lab
Research Open-sourcing DeepMind Lab Published 3 December 2016 Authors Charlie Beattie, Joel Leibo, Stig Petersen, Shane Legg DeepMind's scientific mission is to push the boundaries of AI, developing systems that can learn to solve any complex probl em without needing to be taught how. To achieve this, we work from the premise that AI needs to be general. Agents should operate across a wide range of
chess-news 2017/05/27
æ©Ÿæ¢°å¦ç¿’

AIè¨“ç·´ãƒ—ãƒ©ãƒƒãƒˆãƒ•ã‚©ãƒ¼ãƒ

development

deeplearning

business

AI
ãƒªãƒ³ã‚¯
Amazon.co.jp: ã‚¼ãƒã‹ã‚‰ä½œã‚‹Deep Learning â€•Pythonã§å¦ã¶ãƒ‡ã‚£ãƒ¼ãƒ—ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°ã®ç†è«–ã¨å®Ÿè£…: æ–Žè—¤åº·æ¯…: æœ¬
chess-news 2016/12/24
book

development

Python

æœ¬

oreilly

deep learning

deeplearning
ãƒªãƒ³ã‚¯
Chainerã«ã‚ˆã‚‹ç•³ã¿è¾¼ã¿ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã®å®Ÿè£… - äººå·¥çŸ¥èƒ½ã«é–¢ã™ã‚‹æ–å‰µéŒ²
Chainerã«ã‚ˆã‚‹å¤šå±¤ãƒ‘ãƒ¼ã‚»ãƒ—ãƒˆãƒãƒ³ã®å®Ÿè£…ï¼ˆ2015/10/5ï¼‰ã®ã¤ã¥ãã€‚ä»Šå›žã¯Chainerã§ç•³ã¿è¾¼ã¿ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ï¼ˆCNN:Convolutional Neural Networkï¼‰ã‚’å®Ÿè£…ã—ãŸã€‚Theanoã«ã‚ˆã‚‹ç•³ã¿è¾¼ã¿ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã®å®Ÿè£… (1)ï¼ˆ2015/6/26ï¼‰ã§æ›¸ã„ãŸã®ã¨åŒã˜æ§‹é€ ã‚’Chainerã§è©¦ã—ãŸã ã‘ã€‚ã‚¿ã‚¹ã‚¯ã¯å‰å›žã¨åŒã˜ãMNISTã€‚ ä»Šå›žã¯ã€MNISTãƒ‡ãƒ¼ã‚¿ã®å–å¾—ã‚„è¨“ç·´/ãƒ†ã‚¹ãƒˆã®åˆ†å‰²ã«scikit-learnã®é–¢æ•°ã‚’ä½¿ã£ã¦ã¿ãŸã€‚ Chainerã§ç•³ã¿è¾¼ã¿ã‚’ã™ã‚‹ãŸã‚ã«ã¯ã€è¨“ç·´ãƒ‡ãƒ¼ã‚¿ã®ç”»åƒã‚»ãƒƒãƒˆã‚’ï¼ˆãƒŸãƒ‹ãƒãƒƒãƒã‚µã‚¤ã‚ºã€ãƒãƒ£ãƒ³ãƒãƒ«æ•°ã€é«˜ã•ã€å¹…ï¼‰ã®4æ¬¡å…ƒãƒ†ãƒ³ã‚½ãƒ«ã«å¤‰æ›ã™ã‚‹å¿…è¦ãŒã‚ã‚‹ï¼ˆã“ã“ã«æ›¸ã„ã¦ã‚ã‚‹ï¼‰ã€‚ä»Šå›žã¯ãƒãƒ£ãƒ³ãƒãƒ«æ•°ãŒ1ãªã®ã§å˜ç´”ã«reshapeã§å¤‰å½¢ã§ãã‚‹ã€‚ 3ãƒãƒ£ãƒ³ãƒãƒ«ã®ã‚«ãƒ©ãƒ¼ç”»åƒã ã¨numpyã®transpose()ã§4æ¬¡å…ƒãƒ†ãƒ³ã‚½ãƒ«ã«å¤‰æ›ã§ãã‚‹ã¿ãŸã„
chess-news 2016/02/02
æ©Ÿæ¢°å¦ç¿’

CNN

deeplearning

machinelearning

development

deep learning

MNIST
ãƒªãƒ³ã‚¯
è¤‡åˆæ©Ÿæ¢°å¦ç¿’ã«ã‚ˆã‚‹åˆ†æ•£ãƒ‡ãƒ¼ã‚¿å‡¦ç†ã§ã•ã™ãŒã«è‰¯ãå‡ºæ¥ã¦ã‚‹TensorFlow
å…¨è„³ã‚¢ãƒ¼ã‚ãƒ†ã‚¯ãƒãƒ£ãƒ»ã‚¤ãƒ‹ã‚·ã‚¢ãƒ†ã‚£ãƒ–å‰¯ä»£è¡¨ã®é«˜æ©‹ã§ã™ã€‚ å··ã§è©±é¡Œã®TensorFlow(TF)ã®white paperã¨ã‚½ãƒ¼ã‚¹è¦‹ã¾ã—ãŸã€‚ã‚½ãƒ¼ã‚¹ã‚‚è¦‹ã¾ã—ãŸãŒã€whitepaperãŒã¨ã¦ã‚‚ã‚ˆãæ›¸ã‘ã¦ã‚‹ã®ã§ã“ã‚Œã ã‘ã§å¤§ä½“è¨è¨ˆãŒç†è§£ã§ãã‚‹ã‚ˆã†ã«ãªã£ã¦ã¾ã™ã€‚ ã§ã€çµè«–ã‹ã‚‰ã§ã™ãŒã€ã“ã‚Œã•ã™ãŒã¨ã„ã†ã‹ã™ã”ãã‚ˆãå‡ºæ¥ã¦ã¾ã™ã€‚ ãŸã ã€ãƒãƒœãƒƒãƒˆãƒŸãƒ‰ãƒ«ã‚¦ã‚§ã‚¢ã®ROSãªã©ã‚ˆã‚Šã‹ã¯ãƒ‡ãƒ¼ã‚¿è§£æžã‚½ãƒ•ãƒˆã‚¦ã‚¨ã‚¢ã«è¿‘ãã€ã“ã‚Œã¨æ¯”ã¹ã‚‹ã¨BriCAã¯ã‹ãªã‚ŠROSã«è¿‘ã„ã§ã™ã€‚ ä½•ãŒé•ã†ã‹ã§ã™ãŒï¼›ã€€TFã¯å¤šæ¬¡å…ƒé…åˆ—ï¼ˆãƒ†ãƒ³ã‚½ãƒ«ï¼‰ã«å¯¾ã™ã‚‹æ“ä½œã‚’å®šç¾©ã™ã‚‹ã‚«ãƒ¼ãƒãƒ«ï¼ˆæ£ç¢ºã«è¨€ã†ã¨æŠ½è±¡æ“ä½œã®operationã«ãƒ‘ãƒ©ãƒ¡ãƒ¼ã‚¿ã‚’ä¸Žãˆã¦å…·ä½“çš„ãªè¨ˆç®—æ‰‹é †ã«ã—ãŸã®ãŒã‚«ãƒ¼ãƒãƒ«ï¼‰ã‚’æœ‰å‘ã‚°ãƒ©ãƒ•ã§è¡¨ã—ã¦ã€ã‚°ãƒ©ãƒ•å…¨ä½“ã§ãªã‚“ã‚‰ã‹ã®ãƒ‡ãƒ¼ã‚¿å‡¦ç†ãƒ‘ã‚¤ãƒ—ãƒ©ã‚¤ãƒ³ã‚’è¡¨ç¾ã€å®Ÿè¡Œã—ã¾ã™ã€‚ ã“ã®å ´åˆã®ã‚°ãƒ©ãƒ•ã¯BriCAã‚„ROSã§ã„ã†ã¨ã“ã‚ã®ãƒŽãƒ¼ãƒ‰ã‚„ãƒ¢ã‚¸ãƒ¥ãƒ¼ãƒ«ã‚’çµåˆã—ãŸèªçŸ¥ã‚¢ãƒ¼ã‚ã‚„ãƒãƒœãƒƒãƒˆ
chess-news 2015/11/24
ã‚„ã£ã±ã‚Šã€åŒã˜æ„Ÿã˜ã‚ã‚‹ã‚ˆã

ãƒŽãƒ¼ãƒ‰

ã‚°ãƒ©ãƒ•

ãƒ†ãƒ³ã‚½ãƒ«

ã‚¢ãƒ¼ã‚ãƒ†ã‚¯ãƒãƒ£

machine_learning

ros

TensorFlow
ãƒªãƒ³ã‚¯
æ·±å±¤å¦ç¿’ â€” Deep Learning
æœ¬æ›¸ã®æ¦‚è¦ æ·±å±¤å¦ç¿’ã¯ï¼Œ2012å¹´ã«è¡Œã‚ã‚ŒãŸç”»åƒèªè˜ã®ã‚³ãƒ³ãƒšãƒ†ã‚£ã‚·ãƒ§ãƒ³ã§å„ªã‚ŒãŸæˆç¸¾ã‚’åŽã‚ï¼Œæ€¥é€Ÿã«æ³¨ç›®ã•ã‚Œã‚‹ã‚ˆã†ã«ãªã£ãŸæ©Ÿæ¢°å¦ç¿’ã®æŠ€è¡“ã§ã™ï¼Ž æœ¬æ›¸ã¯ï¼Œ2013å¹´5æœˆã€œ2014å¹´7æœˆã®7å›žã«ã‚ãŸã‚‹äººå·¥çŸ¥èƒ½å¦ä¼šèªŒã§ã®é€£è¼‰è§£èª¬ã€ŒDeepLearningï¼ˆæ·±å±¤å¦ç¿’ï¼‰ã€ã«å¤§å¹…ãªåŠ ç†ã‚’è¡Œã„ï¼Œç´¢å¼•ãªã©ã‚’è¿½åŠ ã—ã¦æ›¸ç±ã¨ã—ã¦ã¾ã¨ã‚ãŸã‚‚ã®ã§ã™ï¼Ž2015å¹´æ™‚ç‚¹ã§ã®æ·±å±¤å¦ç¿’ã«ã¤ã„ã¦ã®ã»ã¨ã‚“ã©ã®è©±é¡Œã«ã¤ã„ã¦è§£èª¬ã—ã¦ã„ã¾ã™ï¼Ž å„ç« ã¯ç‹¬ç«‹ã—ãŸèªã¿ç‰©ã¨ãªã£ã¦ãŠã‚Šï¼Œãã‚Œãžã‚Œã®è©±é¡Œã«ã¤ã„ã¦å€‹åˆ¥ã«çŸ¥ã‚‹ã“ã¨ãŒã§ãã¾ã™ï¼Žä¸€æ–¹ã§ï¼Œç´¢å¼•ã‚’å……å®Ÿã•ã›ã¦ï¼Œæ·±å±¤å¦ç¿’ã«é–¢ã™ã‚‹æ§˜ã€…ãªã‚ãƒ¼ãƒ¯ãƒ¼ãƒ‰ã«ã¤ã„ã¦èª¿ã¹ã‚‹ã“ã¨ãŒã§ãã‚‹ã‚ˆã†ã«ã‚‚ã—ã¾ã—ãŸï¼Ž ä¸€æ–¹ã§ï¼Œå¤šæ•°ã‚ã‚‹æ·±å±¤å¦ç¿’ã®ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢ã‚’ç”¨ã„ã‚‹æ–¹æ³•ã«ã¤ã„ã¦ã¯è¿°ã¹ã¦ã„ã¾ã›ã‚“ï¼Žæœ¬æ›¸ã¯ã“ã‚Œã‚‰ã®ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢ã‚’èª¤ç”¨ã—ãªã„ãŸã‚ã«ï¼Œæ·±å±¤å¦ç¿’ã®å‹•ä½œåŽŸç†ã‚’ç´¹ä»‹ã—ï¼Œå„æ‰‹æ³•ã®é©ç”¨å¯èƒ½ç¯„å›²ã‚’çŸ¥ã£ã¦ã„ãŸã ããŸã‚ã®ã‚‚ã®ã§ã™ï¼Ž é–¢é€£æƒ…å ±
chess-news 2015/11/14
deeplearning

development

deep_learning

deep learning
ãƒªãƒ³ã‚¯
TensorFlowã‚’ç®—æ•°ã§ç†è§£ã™ã‚‹ - Qiita
Deleted articles cannot be recovered. Draft of this article would be also deleted. Are you sure you want to delete this article? TensorFlowã¯ä¸»ã«æ©Ÿæ¢°å¦ç¿’ã€ç‰¹ã«å¤šå±¤ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯(ãƒ‡ã‚£ãƒ¼ãƒ—ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°)ã‚’å®Ÿè£…ã™ã‚‹ãŸã‚ã®ãƒ©ã‚¤ãƒ–ãƒ©ãƒªã«ãªã‚Šã¾ã™ãŒã€ãã®åŸºæœ¬çš„ãªä»•çµ„ã¿ã‚’ç†è§£ã™ã‚‹ã®ã«ãã†ã—ãŸé›£ã—ã„è©±ã¯ç‰¹ã«å¿…è¦ã‚ã‚Šã¾ã›ã‚“ã€‚ æœ¬è¨˜äº‹ã§ã¯ã€TensorFlowã®ä»•çµ„ã¿ã‚’ã€ç®—æ•°ç¨‹åº¦ã®ç°¡å˜ãªè¨ˆç®—ã‚’ãƒ™ãƒ¼ã‚¹ã«ç´è§£ã„ã¦ã„ããŸã„ã¨æ€ã„ã¾ã™ã€‚ TensorFlowã®ç‰¹å¾´ åˆã‚ã«ã€TensorFlowã®ç‰¹å¾´ã«ã¤ã„ã¦ã¾ã¨ã‚ã¦ãŠããŸã„ã¨æ€ã„ã¾ã™ã€‚ TensorFlowã¯ã€ãã®åå‰ã®é€šã‚ŠTensor(å¤šæ¬¡å…ƒé…åˆ—ã€è¡Œåˆ—ãªã©ã«ç›¸å½“)ã®Flow(è¨ˆç®—å‡¦ç†)ã‚’è¨˜è¿°ã™ã‚‹ãŸã‚ã®ãƒ„ãƒ¼ãƒ«ã§ã™ã€‚ãã®ç‰¹å¾´
chess-news 2015/11/13
ã‚°ãƒ©ãƒ• è§£èª¬ã€€è¨ˆç®—ã‹ã‚‰ã€€ãªã‚“ã‹simulinkæ„Ÿã‚ã‚‹ãªã€‚

TensorFlow

Python

MachineLearning

æ©Ÿæ¢°å¦ç¿’

Google

DeepLearning

development
ãƒªãƒ³ã‚¯
OpenCVã§çŒ«æ¤œå‡º (ãƒ¢ãƒ‡ãƒ«é…å¸ƒ) - Qiita
(2014/09è¿½è¨˜) Deep Learning (ãƒ‡ã‚£ãƒ¼ãƒ—ãƒ©ãƒ¼ãƒ‹ãƒ³ã‚°ã€æ·±å±¤å¦ç¿’) ã®æŠ€è¡“ã‚’ç”¨ã„ã¦ã€çŒ«ã®å“ç¨®ã‚’è˜åˆ¥ã™ã‚‹æ–¹æ³•ã®è¨˜äº‹ã‚‚æ›¸ã„ã¦ã„ã¾ã™ã€‚ã‚‚ã—èˆˆå‘³ãŒã‚ã‚Œã°ã”å‚ç…§ãã ã•ã„ã€‚ Deep Learningã§çŒ«ã®å“ç¨®è˜åˆ¥ (ã‚·ãƒ§ã‚³ãƒ© - å‰ç¥¥å¯º ãã‚ƒã‚Šã“) ãã“ã¨ç”»åƒå‡¦ç† part 1 â€“ ç´ æé›†ã‚ã§ã¯çŒ«ç”»åƒã®é›†ã‚æ–¹ã«ã¤ã„ã¦æ•´ç†ã—ã¾ã—ãŸãŒã€ã“ã“ã§ã¯ãã®é›†ã‚ãŸçŒ«ç”»åƒã‚’ä½¿ã£ã¦çŒ«æ¤œå‡ºç”¨ã®å¦ç¿’ãƒ¢ãƒ‡ãƒ«(åˆ†é¡žå™¨)ã‚’ä½œæˆã—ã¾ã—ãŸã€‚ æŠ€è¡“çš„ãªå†…å®¹è©³ç´°ã«ã¤ã„ã¦ã¯ãƒ–ãƒã‚°ã®æ–¹ã«æ›¸ã„ã¦ã‚ã‚Šã¾ã™ã®ã§èˆˆå‘³ãŒã‚ã‚Œã°ã€‚ãƒ¢ãƒ‡ãƒ«é…å¸ƒã«ã¤ã„ã¦ã¯ã“ã®ã‚¨ãƒ³ãƒˆãƒªãƒ¼ã®å¾ŒåŠã§èª¬æ˜Žã—ã¾ã™ã€‚ ãã“ã¨ç”»åƒå‡¦ç† part 2 â€“ çŒ«æ¤œå‡º å¦ç¿’ã¯ãŠé¦´æŸ“ã¿ã®Boosting(ã‚¢ãƒ³ã‚µãƒ³ãƒ–ãƒ«å¦ç¿’æ‰‹æ³•ã®1ã¤)ã§ã€‚ç‰¹å¾´é‡ã¯ãƒ¢ãƒ‡ãƒ«ä½œæˆã¨æ¤œè¨¼ã‚’é€Ÿãç¹°ã‚Šè¿”ã™ã“ã¨ãŒã§ãã‚‹LBPç‰¹å¾´ã‚’æŽ¡ç”¨ã—ã¾ã—ãŸã€‚ã¾ãŸã€ç´„7,000æžšã®ã‚¢ãƒŽãƒ†ãƒ¼ã‚·ãƒ§ãƒ³ãƒ‡ãƒ¼ã‚¿ã¯ã‚¯ãƒ©ã‚¦ãƒ‰ã‚½ãƒ¼ã‚·ãƒ³ã‚°ã‚’æ´»ç”¨
chess-news 2015/08/10
CV(cat vision) çŒ«æ¤œå‡º

cv

æ©Ÿæ¢°å¦ç¿’

ComputerVision

OpenCV

DeepLearning

development
ãƒªãƒ³ã‚¯
Deep Learning ãƒªãƒ³ã‚¯é›† - äººå·¥çŸ¥èƒ½ã«é–¢ã™ã‚‹æ–å‰µéŒ²
ä¹—ã‚‹ã—ã‹ãªã„ã“ã®ãƒ“ãƒƒã‚°ã‚¦ã‚§ãƒ¼ãƒ–ã« Deep Learningï¼ˆæ·±å±¤å¦ç¿’ï¼‰ã«é–¢é€£ã™ã‚‹ã¾ã¨ã‚ãƒšãƒ¼ã‚¸ã¨ã—ã¦ä½¿ç”¨ã™ã‚‹äºˆå®šã§ã™ã€‚Deep Learningã«é–¢ã™ã‚‹è¨˜äº‹ãƒ»ã‚¹ãƒ©ã‚¤ãƒ‰ãƒ»è«–æ–‡ãƒ»å‹•ç”»ãƒ»æ›¸ç±ã¸ã®ãƒªãƒ³ã‚¯ã‚’ã¾ã¨ã‚ã¦ã„ã¾ã™ã€‚æœ€æ–°ã®ç ”ç©¶å‹•å‘ã¯å…¨ç„¶æŠŠæ¡ã§ãã¦ã„ãªã„ã®ã§ä»Šå¾Œç ”ç©¶ã‚’é€²ã‚ã‚‹ãªã‹ã§è¨˜éŒ²ã—ã¦ã„ããŸã„ã¨æ€ã„ã¾ã™ã€‚èªã‚“ã è«–æ–‡ã®æ¦‚è¦ã‚‚ç°¡å˜ã«ã¾ã¨ã‚ã¦ã„ãäºˆå®šã§ã™ã€‚æœ¬ãƒ–ãƒã‚°ã§ã¯ã€å½“é¢ã®é–“ã€Theanoã‚’ä½¿ã£ã¦å„ç¨®Deep Learningã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ ã‚’å®Ÿè£…ã—ã¦ã„ããŸã„ã¨æ€ã„ã¾ã™ã€‚ é–¢é€£ãƒ‹ãƒ¥ãƒ¼ã‚¹ãªã©ã¯Twitterã§ã‚‚æµã—ã¦ã„ã‚‹ã®ã§èˆˆå‘³ãŒã‚ã£ãŸã‚‰ãƒ•ã‚©ãƒãƒ¼ã—ã¦ãã ã•ã„ã€‚ ã™ã¹ã¦ã«ç›®ãŒé€šã›ãšæ›´æ–°ãŒè¿½ã„ã¤ã„ã¦ã„ã¾ã›ã‚“ã€‚ç§ã®ã¯ã¦ãªãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯ã§[Deep Learning]ã¨ã„ã†ã‚¿ã‚°ã‚’ä»˜ã‘ã¦ç™»éŒ²ã—ã¦ã„ã¾ã™ã€‚ã¾ã£ãŸãæ•´ç†ã§ãã¦ã„ã¾ã›ã‚“ãŒã”å‚è€ƒã¾ã§ã€‚ Theanoç·¨ Theanoã‚’Windowsã«ã‚¤ãƒ³ã‚¹ãƒˆãƒ¼ãƒ«ï¼ˆ2015/1
chess-news 2015/04/29
æœ¬

æ©Ÿæ¢°å¦ç¿’

deep learning

deeplearning

development

äººå·¥çŸ¥èƒ½

machinelearning

ã¾ã¨ã‚
ãƒªãƒ³ã‚¯
1