CDLEã¨ã¯ | CDLE
3万人を超ãˆã‚‹æ—¥æœ¬æœ€å¤§ã®AIコミュニテイ。 ディープラーニング社会実装ã®æ—¥æœ¬ä»£è¡¨ã¨ã—ã¦ç¤¾ä¼šã‚’発展ã•ã›ã‚‹ã‚¨ãƒãƒ³ã‚¸ã‚§ãƒªã‚¹ãƒˆãŸã¡ã®é›†ã¾ã‚Šã€‚ JDLA（一般社団法人日本ディープラーニングå”会）ãŒå®Ÿæ–½ã™ã‚‹ã€G検定/Eè³‡æ ¼è©¦é¨“ã®åˆæ ¼è€…ã®ã¿ãŒå‚åŠ ã§ãる。 å¦ã¶ CDLEメンãƒãƒ¼åŒå£«ãŒå¦ã³ã‚ã„ã€ãƒ‡ã‚£ãƒ¼ãƒ—ラーニングã«é–¢ã™ã‚‹çŸ¥è˜ã‚„経験を共有ã™ã‚‹ã€‚ 繋ãŒã‚‹ CDLEメンãƒãƒ¼ãŒäº¤æµã‚’æ·±ã‚ã€ç¹‹ãŒã‚Šã‚’æŒã¤ã€‚繋ãŒã‚‹ã“ã¨ã«ã‚ˆã‚Šã€åŠ©ã‘åˆãˆã‚‹ã€æ¥½ã—ã„ã€å¦ã¹ã‚‹ã€èª²é¡ŒãŒè§£æ±ºã™ã‚‹ã€è‡ªå·±æˆé•·ãªã©ã€å€‹ã€…ã®CDLEå‚åŠ ã®ç›®çš„ãŒé”æˆã•ã‚Œã‚‹ã€‚ 使ㆠ共通課題をæŒã¤ä»²é–“を増やã—ã€ãƒ‡ã‚£ãƒ¼ãƒ—ラーニングã®çŸ¥è˜ã¨çµŒé¨“を活用ã—ã€ç¤¾ä¼šå®Ÿè£…ã™ã‚‹ã€‚
How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of deep RL research has focused on applications in video games and simulated control, which does not connect with the constraints of learning in real environments, deep RL has also demonstrated promise in enabling physical ro
機械å¦ç¿’å·¥å¦ç ”究会（MLSE）
機械å¦ç¿’å·¥å¦ç ”究会（MLSE）ã¯ã€æ©Ÿæ¢°å¦ç¿’システムã®é–‹ç™ºãƒ»é‹ç”¨ã«ã¾ã¤ã‚る生産性やå“質ã®å‘上を追求ã™ã‚‹ç ”究者ã¨ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢ãŒã€äº’ã„ã®ç ”究やプラクティスを共有ã—åˆã†ä¼šã§ã™ã€‚ 2018年度よりã€æ—¥æœ¬ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢ç§‘å¦ä¼šã®å…¬å¼ç ”究会ã¨ãªã‚Šã¾ã™ã€‚ 何をã™ã‚‹ã®ï¼Ÿ è¿‘å¹´ã®æ©Ÿæ¢°å¦ç¿’ã€ã‚ã‚‹ã„ã¯æ·±å±¤å¦ç¿’（ディープラーニング）ã®ç™ºå±•ã«ä¼´ã£ã¦ã€æ©Ÿæ¢°å¦ç¿’を利用ã™ã‚‹ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢ã¯æ€¥é€Ÿã«ç¤¾ä¼šã«æµ¸é€ã—ã¤ã¤ã‚ã‚Šã¾ã™ã€‚ã—ã‹ã—ãã®ä¸€æ–¹ã¦ã‚™ã€ã“ã‚Œã¾ã§ã®ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢å·¥å¦ã¯ã€æ©Ÿæ¢°å¦ç¿’を組ã¿è¾¼ã‚“ã システム（機械å¦ç¿’システム）ã®å‰ã«å…¨ãã¨è¨€ã£ã¦ã„ã„ã»ã¨ã‚™é€šç”¨ã—ãªããªã£ã¦ã—ã¾ã£ã¦ã„ã¾ã™ã€‚機械å¦ç¿’ソフトウェアã®é–‹ç™ºãƒ»ãƒ†ã‚¹ãƒˆãƒ»é‹ç”¨ã®æ–¹æ³•è«–ã¯æœªãŸã‚™ã«ç¢ºç«‹ã¦ã‚™ãã¦ãŠã‚‰ã™ã‚™ã€é–‹ç™ºç¾å ´ã¦ã‚™ã¯ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢é”ãŒè©¦è¡ŒéŒ¯èª¤ã§ãªã‚“ã¨ã‹å‡Œã„ã§ã„る状æ³ã§ã™ã€‚ ã“ã®ã‚ˆã†ãªç¾çŠ¶ã‚’è¸ã¾ãˆã€æ©Ÿæ¢°å¦ç¿’システムã«å¯¾ã—ã¦ã¯ã€Œæ©Ÿæ¢°å¦ç¿’å·¥å¦ã€ã¨ã‚‚ã„ã†ã¸ã‚™ãã€æ–°ãŸãªãƒã‚šãƒ©ã‚¿ã‚™ã‚¤ãƒ ã®ç¢ºç«‹ãƒ»ä½“
Software 2.0
I sometimes see people refer to neural networks as just “another tool in your machine learning toolboxâ€. They have some pros and cons, they work here or there, and sometimes you can use them to win Kaggle competitions. Unfortunately, this interpretation completely misses the forest for the trees. Neural networks are not just another classifier, they represent the beginning of a fundamental shift i
iMLSE 2020
Keynote Speaker:​ ​ ​ ​ ​ ​ Clark Barrett (Associate Professor at Computer Science of Stanford University, Co-Director of Center for AI Safety, USA) Title: Towards Rigorous Verification for Safe Artificial Intelligence Biography: Clark Barrett joined Stanford University as an Associate Professor (Research) of Computer Science in September 2016. Before that, he was an Associate Professor of Comput
機械å¦ç¿’å·¥å¦ç ”究会ã‚ックオフシンãƒã‚¸ã‚¦ãƒ ã¯ã€Œæ¥ç•Œã‚ã‚‹ã‚ã‚‹ã€ã¨ã€Œå…±æ„Ÿã€ã«æº€ã¡ã¦ã„㟠〜イベントレãƒãƒ¼ãƒˆã€œ | LeapMind inc.
5/17ã«é–‹å‚¬ã•ã‚ŒãŸã€æ©Ÿæ¢°å¦ç¿’å·¥å¦ç ”究会ã‚ックオフシンãƒã‚¸ã‚¦ãƒ ã¨ã„ã†ã‚¤ãƒ™ãƒ³ãƒˆã«å‚åŠ ã—ã¦ãã¾ã—ãŸï¼ 機械å¦ç¿’特有ã®èª²é¡Œã‚’見æ®ãˆãªãŒã‚‰ã€æ—¢å˜ã®ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢å·¥å¦ã‚’ベースã«ã—ãªãŒã‚‰ä»Šå¾Œã®æ©Ÿæ¢°å¦ç¿’システムã®é–‹ç™ºãƒ»é‹ç”¨ã«ãŠã‘ã‚‹å“質や開発手法を一緒ã«è€ƒãˆè°è«–ã™ã‚‹å ´ã§ã‚ã‚Šã€æ§˜ã€…ãªç«‹å ´ã®æ–¹ã€…ã‹ã‚‰ã®è¦–点ã§ã‹ãªã‚Šè©³ç´°ã«èª²é¡Œæèµ·ã—ã¦ã„る会ã§ã—ãŸã€‚ 機械å¦ç¿’ã«ãŠã‘る課題ã¯ã€æ©Ÿæ¢°å¦ç¿’関連ã®ä¼æ¥ã«å‹¤ã‚ã¦ã„る人ãŸã¡ã®é–“ã§ã¯ã€ãªã‚“ã¨ãªã解釈ã•ã‚Œã¦ã„ã¦ã€æš—é»™ã®äº†è§£ã®ã‚ˆã†ã«çš†å…±é€šã§æ„Ÿã˜ã¦ã„ã‚‹ã“ã¨ãŒå¤šãã‚ã‚‹ã®ã§ã™ãŒã€ä¸€æ©å¤–ã«å‡ºã‚‹ã¨ã€èª²é¡Œã¯ã‚‚ã¡ã‚ã‚“ç†è§£ã•ã‚Œã¦ã„ãªã„ã—ã€æ©Ÿæ¢°å¦ç¿’ãŒé”法ã‹ã®ã‚ˆã†ãªæ‰±ã„ã‚’å—ã‘ã‚‹ã“ã¨ãŒå¤šã€…ã‚ã‚Šã¾ã™ã€‚ （発注者ã¨å—注者ã®é–“ã§å·»ãèµ·ã“る論争。。。。） Twitterãªã©ã§ã€èª²é¡Œæ示ã—ã¦ã„る人もã„ã¾ã™ãŒã€å¤§æŠµã¯ã€æ–‡ç« é‡ã®å°‘ãªã•ã‚„背景知è˜ã®å·®ãŒå¤§ãã™ãŽã¦ã€ãƒžã‚¦ãƒ³ãƒˆã‚’ã¨ã£ã¦ã„るよã†ã«èžã“ãˆã‚‹ã“ã¨ãŒå¤šãã€éŽåŽ»ç‚Žä¸Šã—ã¦ã„
機械å¦ç¿’å·¥å¦ç ”究会（MLSE） - 資料一覧 - connpass
「機械å¦ç¿’å·¥å¦ç ”究会（MLSE）ã€ã®è³‡æ–™ä¸€è¦§ã§ã™ã€‚
MLSE
機械å¦ç¿’å·¥å¦ç ”究会（MLSE）ã¯ã€æ©Ÿæ¢°å¦ç¿’システムã®é–‹ç™ºãƒ»é‹ç”¨ã«ã¾ã¤ã‚る生産性やå“質ã®å‘上を追求ã™ã‚‹ç ”究者ã¨ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢ãŒã€äº’ã„ã®ç ”究やプラクティスを共有ã—åˆã†ä¼šã§ã™ã€‚ 2018年度よりã€æ—¥æœ¬ã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢ç§‘å¦ä¼šã®å…¬å¼ç ”究会ã¨ã—ã¦æ£å¼ã«ç™ºè¶³ã—ã¾ã—ãŸã€‚ è¿‘å¹´ã®æ©Ÿæ¢°å¦ç¿’ã€ã‚ã‚‹ã„ã¯æ·±å±¤å¦ç¿’（ディープラーニング）ã®ç™ºå±•ã«ä¼´ã£ã¦ã€æ©Ÿæ¢°å¦ç¿’を利用ã™ã‚‹ã‚·ã‚¹ãƒ†ãƒ ã¯æ€¥é€Ÿã«ç¤¾ä¼šã«æµ¸é€ã—ã¤ã¤ã‚ã‚Šã¾ã™ã€‚ã—ã‹ã—ãã®ä¸€æ–¹ã¦ã‚™ã€å¾“æ¥åž‹ã®ITシステムã«ç”¨ã„られã¦ããŸæ§˜ã€…ãªã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢å·¥å¦çš„手法ã¯ã€æ©Ÿæ¢°å¦ç¿’を組ã¿è¾¼ã‚“ã システム（機械å¦ç¿’システム）ã®å‰ã«å…¨ãã¨è¨€ã£ã¦ã„ã„ã»ã¨ã‚™é€šç”¨ã—ãªããªã£ã¦ã—ã¾ã£ã¦ã„ã¾ã™ã€‚機械å¦ç¿’システムã®é–‹ç™ºãƒ»ãƒ†ã‚¹ãƒˆãƒ»é‹ç”¨ã®æ–¹æ³•è«–ã¯æœªãŸã‚™ã«ç¢ºç«‹ã¦ã‚™ãã¦ãŠã‚‰ã™ã‚™ã€é–‹ç™ºç¾å ´ã¦ã‚™ã¯ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢é”ãŒè©¦è¡ŒéŒ¯èª¤ã§ãªã‚“ã¨ã‹å‡Œã„ã§ã„る状æ³ã§ã™ã€‚ ã“ã®ã‚ˆã†ãªç¾çŠ¶ã‚’è¸ã¾ãˆã€æ©Ÿæ¢°å¦ç¿’システムã«å¯¾ã—ã¦ã¯ã€Œæ©Ÿæ¢°å¦ç¿’å·¥å¦ã€ã¨ã‚‚ã„ã†ã¸ã‚™ãã€
PyTorch
Join us in Silicon Valley September 18-19 at the 2024 PyTorch Conference. Learn more. Learn Get Started Run PyTorch locally or get started quickly with one of the supported cloud platforms Tutorials Whats new in PyTorch tutorials Learn the Basics Familiarize yourself with PyTorch concepts and modules PyTorch Recipes Bite-size, ready-to-deploy PyTorch code examples Intro to PyTorch - YouTube Series
ONNX
Open Neural Network Exchange The open standard for machine learning interoperability Get Started ONNX is an open format built to represent machine learning models. ONNX defines a common set of operators - the building blocks of machine learning and deep learning models - and a common file format to enable AI developers to use models with a variety of frameworks, tools, runtimes, and compilers. LEA
GitHub - lutzroeder/netron: Visualizer for neural network, deep learning and machine learning models
深層å¦ç¿’ã¯ã‚·ã‚¹ãƒ†ãƒ 1ã‹ã‚‰ã‚·ã‚¹ãƒ†ãƒ 2ã¸
日本ディープラーニングå”会（以下JDLA）ã®å¹´é 所感[1]ã®ä¸ã§ã€æ±äº¬å¤§å¦ã®æ¾å°¾ 豊教授ã¯ã€æ¬¡ã®ã‚ˆã†ã«è¿°ã¹ã¦ã„ã¾ã™ã€‚ 今後ã€ãƒ‡ã‚£ãƒ¼ãƒ—ラーニングã®æŠ€è¡“ã¯ã•ã‚‰ã«é€²ã‚“ã§ã„ãã¾ã™ã€‚ãƒãƒœãƒƒãƒˆã‚„機械ã¸ã®å¿œç”¨ã€ãã—ã¦è¨€èªžã®å‡¦ç†ã®ãƒ–レークスルーã¸ã¨é€²ã‚“ã§ã„ãã¯ãšã§ã™ã€‚昨年末ã€NeurIPS 2019ã§Bengioæ°ãŒè¡Œã£ãŸè¬›æ¼”ã¯ã€ã‚·ã‚¹ãƒ†ãƒ 1ã®ãƒ‡ã‚£ãƒ¼ãƒ—ラーニングã‹ã‚‰ã‚·ã‚¹ãƒ†ãƒ 2ã®ãƒ‡ã‚£ãƒ¼ãƒ—ラーニングã¸ã¨ã„ã†å†…容ã§ã€ä»Šå¾Œã®æŠ€è¡“ã®åºƒãŒã‚ŠãŒæ„Ÿã˜ã‚‰ã‚Œã‚‹éžå¸¸ã«æŒ‘戦的ãªã‚‚ã®ã§ã—ãŸã€‚ ã“ã“ã§è¨€ã†ã‚·ã‚¹ãƒ†ãƒ 2ã®ãƒ‡ã‚£ãƒ¼ãƒ—ラーニングã¨ã¯ä½•ã§ã—ょã†ã‹ï¼Ÿ 本記事ã§ã¯ã€ã‚·ã‚¹ãƒ†ãƒ 2ã®æœ€å‰ç·šã«ã¤ã„ã¦æŽ¢ã£ã¦ã‚†ãã¾ã™ã€‚ NeurIPS 2019招待講演 Conference and Workshop on Neural Information Processing Systems（略称：NeurIPSã€æ—§ç§°ï¼šNIPS）ã¯ã€æ¯Žå¹´12月ã«é–‹å‚¬ã•ã‚Œã‚‹æ©Ÿ
The Consciousness Prior
A new prior is proposed for learning representations of high-level concepts of the kind we manipulate with language. This prior can be combined with other priors in order to help disentangling abstract factors from each other. It is inspired by cognitive neuroscience theories of consciousness, seen as a bottleneck through which just a few elements, after having been selected by attention from a br
Neural scene representation and rendering
Research Neural scene representation and rendering Published 14 June 2018 Authors Ali Eslami, Danilo Jimenez Rezende There is more than meets the eye when it comes to how we understand a visual scene: our brains draw on prior knowledge to reason and to make inferences that go far beyond the patterns of light that hit our retinas. For example, when entering a room for the first time, you instantly
ランã‚ング
ランã‚ング
ランã‚ング
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
ビデオ会è°ã‚’変é©ã•ã›ã‚‹ GAN ç ”ç©¶ | NVIDIA
Model Zoo — PyTorch/Serve master documentation
Model Zoo
Caffe | Model Zoo
GitHub - onnx/models: A collection of pre-trained, state-of-the-art models in the ONNX format
GitHub - onnx/onnx: Open standard for machine learning interoperability
{{#tags}}- {{label}}
{{/tags}}