æ¾å°¾ãƒ»å²©æ¾¤ç ”究室主催ã®å…¬é–‹è¬›åº§ã€Œå¤§è¦æ¨¡è¨€èªžãƒ¢ãƒ‡ãƒ« 2024ã€ã‚’開講ã—ã¾ã™. å—講を希望ã•ã‚Œã‚‹æ–¹ã¯ä¸‹è¨˜ãƒšãƒ¼ã‚¸ã‚’å‚考ã«ã—ã¦ãã ã•ã„. 大è¦æ¨¡è¨€èªžãƒ¢ãƒ‡ãƒ« 2024 ç”³è¾¼ç· åˆ‡â”‚ more
Deep Learning JP
æ¾å°¾ãƒ»å²©æ¾¤ç ”究室主催ã®å…¬é–‹è¬›åº§ã€Œå¤§è¦æ¨¡è¨€èªžãƒ¢ãƒ‡ãƒ« 2024ã€ã‚’開講ã—ã¾ã™. å—講を希望ã•ã‚Œã‚‹æ–¹ã¯ä¸‹è¨˜ãƒšãƒ¼ã‚¸ã‚’å‚考ã«ã—ã¦ãã ã•ã„. 大è¦æ¨¡è¨€èªžãƒ¢ãƒ‡ãƒ« 2024 ç”³è¾¼ç· åˆ‡â”‚ more
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
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, … amazing interface to C, via
Chainerã«ã‚ˆã‚‹ç•³ã¿è¾¼ã¿ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã®å®Ÿè£… - 人工知能ã«é–¢ã™ã‚‹æ–創録
Chainerã«ã‚ˆã‚‹å¤šå±¤ãƒ‘ーセプトãƒãƒ³ã®å®Ÿè£…（2015/10/5）ã®ã¤ã¥ã。今回ã¯Chainerã§ç•³ã¿è¾¼ã¿ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ï¼ˆCNN:Convolutional Neural Network）を実装ã—ãŸã€‚Theanoã«ã‚ˆã‚‹ç•³ã¿è¾¼ã¿ãƒ‹ãƒ¥ãƒ¼ãƒ©ãƒ«ãƒãƒƒãƒˆãƒ¯ãƒ¼ã‚¯ã®å®Ÿè£… (1)（2015/6/26）ã§æ›¸ã„ãŸã®ã¨åŒã˜æ§‹é€ ã‚’Chainerã§è©¦ã—ãŸã ã‘。タスクã¯å‰å›žã¨åŒã˜ãMNIST。 今回ã¯ã€MNISTデータã®å–得や訓練/テストã®åˆ†å‰²ã«scikit-learnã®é–¢æ•°ã‚’使ã£ã¦ã¿ãŸã€‚ Chainerã§ç•³ã¿è¾¼ã¿ã‚’ã™ã‚‹ãŸã‚ã«ã¯ã€è¨“練データã®ç”»åƒã‚»ãƒƒãƒˆã‚’（ミニãƒãƒƒãƒã‚µã‚¤ã‚ºã€ãƒãƒ£ãƒ³ãƒãƒ«æ•°ã€é«˜ã•ã€å¹…）ã®4次元テンソルã«å¤‰æ›ã™ã‚‹å¿…è¦ãŒã‚る（ã“ã“ã«æ›¸ã„ã¦ã‚る）。今回ã¯ãƒãƒ£ãƒ³ãƒãƒ«æ•°ãŒ1ãªã®ã§å˜ç´”ã«reshapeã§å¤‰å½¢ã§ãる。 3ãƒãƒ£ãƒ³ãƒãƒ«ã®ã‚«ãƒ©ãƒ¼ç”»åƒã ã¨numpyã®transpose()ã§4次元テンソルã«å¤‰æ›ã§ãã‚‹ã¿ãŸã„
RECRUIT TECHNOLOGIES Member's blog NNライブラリChainerã‚’Scikit-learn likeã«ã‚«ã‚™ãƒ³ã‚«ã‚™ãƒ³æ‹¡å¼µã™ã‚‹
from xchainer import NNmanager import numpy as np from chainer import FunctionSet, Variable, optimizers import chainer.functions as F from sklearn.base import ClassifierMixin # NNmanager NNmanager model optimizer lossFunction model chainer.FunctionSetoptimizer chainer.optimizerslossFunction chainer.functions chainer paramsparams epoch batchsize logging forward trimOutput forward trimOutput chain
複åˆæ©Ÿæ¢°å¦ç¿’ã«ã‚ˆã‚‹åˆ†æ•£ãƒ‡ãƒ¼ã‚¿å‡¦ç†ã§ã•ã™ãŒã«è‰¯ã出æ¥ã¦ã‚‹TensorFlow
全脳アーã‚テクãƒãƒ£ãƒ»ã‚¤ãƒ‹ã‚·ã‚¢ãƒ†ã‚£ãƒ–副代表ã®é«˜æ©‹ã§ã™ã€‚ å··ã§è©±é¡Œã®TensorFlow(TF)ã®white paperã¨ã‚½ãƒ¼ã‚¹è¦‹ã¾ã—ãŸã€‚ソースも見ã¾ã—ãŸãŒã€whitepaperãŒã¨ã¦ã‚‚よã書ã‘ã¦ã‚‹ã®ã§ã“ã‚Œã ã‘ã§å¤§ä½“è¨è¨ˆãŒç†è§£ã§ãるよã†ã«ãªã£ã¦ã¾ã™ã€‚ ã§ã€çµè«–ã‹ã‚‰ã§ã™ãŒã€ã“ã‚Œã•ã™ãŒã¨ã„ã†ã‹ã™ã”ãよã出æ¥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€‚ 何ãŒé•ã†ã‹ã§ã™ãŒï¼›ã€€TFã¯å¤šæ¬¡å…ƒé…列（テンソル）ã«å¯¾ã™ã‚‹æ“作を定義ã™ã‚‹ã‚«ãƒ¼ãƒãƒ«ï¼ˆæ£ç¢ºã«è¨€ã†ã¨æŠ½è±¡æ“作ã®operationã«ãƒ‘ラメータを与ãˆã¦å…·ä½“çš„ãªè¨ˆç®—æ‰‹é †ã«ã—ãŸã®ãŒã‚«ãƒ¼ãƒãƒ«ï¼‰ã‚’有å‘グラフã§è¡¨ã—ã¦ã€ã‚°ãƒ©ãƒ•å…¨ä½“ã§ãªã‚“らã‹ã®ãƒ‡ãƒ¼ã‚¿å‡¦ç†ãƒ‘イプラインを表ç¾ã€å®Ÿè¡Œã—ã¾ã™ã€‚ ã“ã®å ´åˆã®ã‚°ãƒ©ãƒ•ã¯BriCAã‚„ROSã§ã„ã†ã¨ã“ã‚ã®ãƒŽãƒ¼ãƒ‰ã‚„モジュールをçµåˆã—ãŸèªçŸ¥ã‚¢ãƒ¼ã‚ã‚„ãƒãƒœãƒƒãƒˆ
深層å¦ç¿’ — Deep Learning
本書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‚，急速ã«æ³¨ç›®ã•ã‚Œã‚‹ã‚ˆã†ã«ãªã£ãŸæ©Ÿæ¢°å¦ç¿’ã®æŠ€è¡“ã§ã™ï¼Ž 本書ã¯ï¼Œ2013å¹´5月〜2014å¹´7月ã®7回ã«ã‚ãŸã‚‹äººå·¥çŸ¥èƒ½å¦ä¼šèªŒã§ã®é€£è¼‰è§£èª¬ã€ŒDeepLearning（深層å¦ç¿’）ã€ã«å¤§å¹…ãªåŠ ç†ã‚’è¡Œã„，索引ãªã©ã‚’è¿½åŠ ã—ã¦æ›¸ç±ã¨ã—ã¦ã¾ã¨ã‚ãŸã‚‚ã®ã§ã™ï¼Ž2015年時点ã§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‚’充実ã•ã›ã¦ï¼Œæ·±å±¤å¦ç¿’ã«é–¢ã™ã‚‹æ§˜ã€…ãªã‚ーワードã«ã¤ã„ã¦èª¿ã¹ã‚‹ã“ã¨ãŒã§ãるよã†ã«ã‚‚ã—ã¾ã—ãŸï¼Ž 一方ã§ï¼Œå¤šæ•°ã‚る深層å¦ç¿’ã®ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢ã‚’用ã„る方法ã«ã¤ã„ã¦ã¯è¿°ã¹ã¦ã„ã¾ã›ã‚“．本書ã¯ã“れらã®ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢ã‚’誤用ã—ãªã„ãŸã‚ã«ï¼Œæ·±å±¤å¦ç¿’ã®å‹•ä½œåŽŸç†ã‚’紹介ã—，å„手法ã®é©ç”¨å¯èƒ½ç¯„囲を知ã£ã¦ã„ãŸã ããŸã‚ã®ã‚‚ã®ã§ã™ï¼Ž é–¢é€£æƒ…å ±
Deep Learning リンク集 - 人工知能ã«é–¢ã™ã‚‹æ–創録
ä¹—ã‚‹ã—ã‹ãªã„ã“ã®ãƒ“ッグウェーブ㫠Deep Learning（深層å¦ç¿’）ã«é–¢é€£ã™ã‚‹ã¾ã¨ã‚ページ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«–文・動画・書ç±ã¸ã®ãƒªãƒ³ã‚¯ã‚’ã¾ã¨ã‚ã¦ã„ã¾ã™ã€‚最新ã®ç ”究動å‘ã¯å…¨ç„¶æŠŠæ¡ã§ãã¦ã„ãªã„ã®ã§ä»Šå¾Œç ”究を進ã‚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„ã予定ã§ã™ã€‚本ブãƒã‚°ã§ã¯ã€å½“é¢ã®é–“ã€Theanoを使ã£ã¦å„種Deep Learningアルゴリズムを実装ã—ã¦ã„ããŸã„ã¨æ€ã„ã¾ã™ã€‚ 関連ニュースãªã©ã¯Twitterã§ã‚‚æµã—ã¦ã„ã‚‹ã®ã§èˆˆå‘³ãŒã‚ã£ãŸã‚‰ãƒ•ã‚©ãƒãƒ¼ã—ã¦ãã ã•ã„。 ã™ã¹ã¦ã«ç›®ãŒé€šã›ãšæ›´æ–°ãŒè¿½ã„ã¤ã„ã¦ã„ã¾ã›ã‚“。ç§ã®ã¯ã¦ãªãƒ–ックマークã§[Deep Learning]ã¨ã„ã†ã‚¿ã‚°ã‚’付ã‘ã¦ç™»éŒ²ã—ã¦ã„ã¾ã™ã€‚ã¾ã£ãŸãæ•´ç†ã§ãã¦ã„ã¾ã›ã‚“ãŒã”å‚考ã¾ã§ã€‚ Theanoç·¨ Theanoã‚’Windowsã«ã‚¤ãƒ³ã‚¹ãƒˆãƒ¼ãƒ«ï¼ˆ2015/1
1
ランã‚ング
ランã‚ング
障害
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
Amazon.co.jp: ゼãƒã‹ã‚‰ä½œã‚‹Deep Learning ―Pythonã§å¦ã¶ãƒ‡ã‚£ãƒ¼ãƒ—ラーニングã®ç†è«–ã¨å®Ÿè£…: 斎藤康毅: 本
{{#tags}}- {{label}}
{{/tags}}