Horizon: The first open source reinforcement learning platform for large-scale products and services
An end-to-end platform built on PyTorch 1.0 that is designed to jump start RL's transition from research papers to production Horizon is the first open source end-to-end platform that uses applied reinforcement learning (RL) to optimize systems in large-scale production environments. The workflows and algorithms included in this release were built on open frameworks — PyTorch 1.0, Caffe2, and Spar
Hardware Accelerators for Machine Learning (CS 217) by cs217
Hardware Accelerators for Machine Learning (CS 217) Stanford University, Winter 2023 This course provides in-depth coverage of the architectural techniques used to design accelerators for training and inference in machine learning systems. This course will cover classical ML algorithms such as linear regression and support vector machines as well as DNN models such as convolutional neural nets, an
統計å¦è‡ªç¿’ノート
多変é‡è§£æž 回帰分æžï¼ˆã‚ã¦ã¯ã‚），判別分æžï¼Œä¸»æˆåˆ†åˆ†æžï¼Œå› å分æž, SEM æ•°é‡åŒ– I 類，数é‡åŒ– II 類，数é‡åŒ– III 類，数é‡åŒ– IV é¡ž æ£æº–相関分æžï¼Œã‚¯ãƒ©ã‚¹ã‚¿ãƒ¼åˆ†æžï¼Œä¸»åº§æ¨™åˆ†æž クãƒãƒ³ãƒãƒƒã‚¯ã® $\alpha$ ä¿¡é ¼æ€§ä¿‚æ•° 生å˜çŽ‡è§£æž Cutler-Ederer 法ã«ã‚ˆã‚‹ç”Ÿå‘½è¡¨ï¼ŒKaplan-Meier 法ã«ã‚ˆã‚‹ç”Ÿå‘½è¡¨ 多é‡ãƒã‚¸ã‚¹ãƒ†ã‚£ãƒƒã‚¯ãƒ¢ãƒ‡ãƒ«ï¼ŒCox ã®æ¯”例ãƒã‚¶ãƒ¼ãƒ‰ãƒ¢ãƒ‡ãƒ«
統計å¦å…¥é–€âˆ’第2ç«
2.4 å·®ã¨æ¯”ã¨ãƒ‘ーセントã®ä½¿ã„分㑠(1) å·®ã¨æ¯”ã®é•ã„ 薬剤ã®æŠ•ä¸Žå‰å¾Œã§è¡€åœ§ã‚’測定ã—ãŸæ™‚ã®ã‚ˆã†ã«ã€å¯¾å¿œã®ã‚ã‚‹2標本データã®è¦ç´„ã‚’ã™ã‚‹å ´åˆã¯å‰å¾Œã®å·®ã‚’計算ã—ã¦å¤‰åŒ–é‡ã«ã—ãŸã‚Šã€å·®ã‚’å‰å€¤ã§å‰²ã£ã¦100を掛ã‘ã€å‰å€¤ã«å¯¾ã™ã‚‹å¤‰åŒ–率ã«ã™ã‚‹ãªã©ã—ã¦1標本データã«é‚„å…ƒã—ã¦æ‰±ã„ã¾ã™ã€‚ 変化é‡ã«ã—ã‚変化率ã«ã—ã‚ã€ã‚ã‚Šã¨ç„¡é€ 作ã«è¨ˆç®—ã—ã¦ã„ã¾ã™ãŒã€å®Ÿã¯ã“ã“ã«ã‚‚統計å¦ã®è½ã¨ã—ç©´ãŒæ½œã‚“ã§ã„ã¾ã™ã€‚ 差や差ã®ãƒ‘ーセントを計算ã™ã‚‹ã¨ã„ã†ã“ã¨ãŒã©ã†ã„ã£ãŸæ„味をæŒã£ã¦ã„ã‚‹ã®ã‹ã€ã“ã“ã§ã‚‚ã†ä¸€åº¦ã—ã£ã‹ã‚Šã¨è€ƒãˆã¦ã¿ã¾ã—ょã†ã€‚ 差を計算ã—ã¦å¤‰åŒ–é‡ã«å¤‰æ›ã™ã‚‹ã®ã¯å€‹ã€…ã®ãƒ‡ãƒ¼ã‚¿ã®å¤‰åŒ–é‡ã‚’比較ã—ãŸã‚Šã€å¤‰åŒ–é‡ã®å¹³å‡å€¤ã‚’求ã‚ã¦å…¨ä½“ã¨ã—ã¦ã©ã®ç¨‹åº¦å¤‰åŒ–ã—ãŸã‹ã‚’è¦ç´„ã—ãŸã‚Šã™ã‚‹ãŸã‚ã§ã™ã€‚ ã—ã‹ã—ã‚‚ã—変化é‡ãŒå‰å€¤ã«ã‚ˆã£ã¦å½±éŸ¿ã‚’å—ã‘ã‚‹ã¨ã™ã‚‹ã¨ã€ä¸€ä½“ã©ã†ã„ã†ã“ã¨ã«ãªã‚‹ã§ã—ょã†ã‹ï¼Ÿ 例ãˆã°è¡€åœ§ã¯å‰å€¤ã®å¤§ããªäººã»ã©ã‚ˆã低下ã™ã‚‹ã¨ã—ã¾ã™ã€‚ ãã†ã™ã‚‹ã¨åŒã˜ã‚ˆã†ã«1
Notes from the AI frontier: Applications and value of deep learning
An analysis of more than 400 use cases across 19 industries and nine business functions highlights the broad use and significant economic potential of advanced AI techniques. Artificial intelligence (AI) stands out as a transformational technology of our digital age—and its practical application throughout the economy is growing apace. For this briefing, Notes from the AI frontier: Insights from h
NIPS'17 Adversarial Learning Competition ã«å‚戦ã—ã¾ã—㟠- Preferred Networks Research & Development
機械å¦ç¿’ã®å›½éš›å¦ä¼š NIPS’17 ã«ä½µè¨ã•ã‚Œ Kaggle ã§é–‹å‚¬ã•ã‚ŒãŸã‚³ãƒ³ãƒ†ã‚¹ãƒˆã€ŒNIPS’17 Adversarial Learning Competitionã€ã« PFN ã®ãƒ¡ãƒ³ãƒãƒ¼ã§å‚åŠ ã—ã€4 ä½å…¥è³žã‚’æžœãŸã™ã“ã¨ãŒã§ãã¾ã—ãŸã€‚ãã®çµæžœã€NIPS’17 ã«æ‹›å¾…ã•ã‚Œç™ºè¡¨ã‚’è¡Œã„ã€æ‰‹æ³•ã«ã¤ã„ã¦ã®è«–文も執ç†ã—公開ã—ã¾ã—ãŸã€‚ソースコードも公開ã—ã¦ã„ã¾ã™ã€‚本記事ã§ã¯ã€å…·ä½“çš„ã«ã©ã†ã„ã£ãŸå†…容ã®ã‚³ãƒ³ãƒ†ã‚¹ãƒˆã ã£ãŸã‹ã‚„ã€æˆ‘々ãŒã©ã®ã‚ˆã†ãªã‚¢ãƒ—ãƒãƒ¼ãƒã§å–り組㿠4 ä½å…¥è³žã‚’é”æˆã—ãŸã®ã‹ã«ã¤ã„ã¦ç´¹ä»‹ã—ã¾ã™ã€‚ Adversarial Example ã¨ã¯ï¼Ÿ Adversarial example [1, 2, 3] ã¯æ·±å±¤å¦ç¿’を実用化ã—ã¦ã„ã上ã§ã®æœ€ã‚‚大ããªèª²é¡Œã® 1 ã¤ã¨ã—ã¦è€ƒãˆã‚‰ã‚Œã¦ã„ã‚‹éžå¸¸ã«ãƒ›ãƒƒãƒˆãªç ”究分野ã§ã™ã€‚ç”»åƒèªè˜ã‚’例ã«å–ã‚‹ã¨ã€å…ƒç”»åƒã«å¯¾ã—人ãŒæ°—ã¥ã‹ãªã„程度ã®åƒ…ã‹ãªå¤‰æ›´ã‚’åŠ ãˆã‚‹ã ã‘ã§ã€CNN ã«ã‚ˆ
異常検知システム開発ã®é›£ã—ã•
ã¯ã˜ã‚㫠「異常検知ã—ãŸã„ã€ã¨è€ƒãˆã¦ã„る人ã¯å¤šã„ã¨æ€ã„ã¾ã™ã€‚ã‚‚ã¯ã‚„囲ç¢ã§ã™ã‚‰æ©Ÿæ¢°ãŒäººé–“を上回る時代ã¨ãªã£ãŸã®ã§ã€ã‚·ã‚¹ãƒ†ãƒ ã®æ•…障を発見ã—ãŸã‚Šã‚¯ãƒ¬ã‚¸ãƒƒãƒˆã‚«ãƒ¼ãƒ‰è©æ¬ºã‚’見ã¤ã‘ãŸã‚Šã¨ã„ã†ç•°å¸¸æ¤œçŸ¥ã‚·ã‚¹ãƒ†ãƒ ã‚‚ã€ãƒ‡ãƒ¼ã‚¿ã‚µã‚¤ã‚¨ãƒ³ã‚¹ã‚’使ãˆã°äººé–“以上ã«å„ªç§€ãªã‚‚ã®ã‚’作れるã®ã§ã¯ãªã„ã‹ï¼Ÿã¨è€ƒãˆã‚‹ã®ã‚‚自然ã§ã—ょã†ã€‚ 一方ã§ã€å®Ÿéš›ã«ç•°å¸¸æ¤œçŸ¥ã‚·ã‚¹ãƒ†ãƒ ã®é–‹ç™ºã«ä¹—り出ã—ã¦ã¿ãŸã‚‚ã®ã®ã€æ„外ã¨ä¸Šæ‰‹ã完æˆã¾ã§è¾¿ã‚Šã¤ã‘ãªã‹ã£ãŸã‚Šã€ã›ã£ã‹ã作ã£ãŸã‘ã‚Œã©ã‚‚çµå±€èª¤æ¤œçŸ¥ã らã‘ã§ãŠè”µå…¥ã‚Šã—ãŸã‚Šã€ã¨ã„ã†ã‚±ãƒ¼ã‚¹ã‚‚ã‚ã‚‹ã®ã§ã¯ãªã„ã‹ã¨æ€ã„ã¾ã™ã€‚ã“ã®è¨˜äº‹ã§ã¯å®Ÿéš›ã«ç•°å¸¸æ¤œçŸ¥ã‚·ã‚¹ãƒ†ãƒ をゼãƒã‹ã‚‰é–‹ç™ºã—ã¦ã¿ãŸçµŒé¨“ã‹ã‚‰ã„ãã¤ã‹ã®ç‚¹ã«ã¤ã„ã¦æ›¸ã„ã¦ã¿ãŸã„ã¨æ€ã„ã¾ã™ã€‚ ã“ã®è¨˜äº‹ã«ã¯ã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ çš„ãªã€æŠ€è¡“çš„ãªçŸ¥è¦‹ã¯å«ã¾ã‚Œã¦ã„ã¾ã›ã‚“。「もã—居酒屋ã§ç•°å¸¸æ¤œçŸ¥ã‚’ãƒã‚¿ã«å‘‘ã‚€ã¨ã—ãŸã‚‰ã€ã“ã®ã¸ã‚“ã§ç››ã‚Šä¸ŠãŒã‚‹ã‹ãªã€çš„ãªè¨˜äº‹ã¨ã—ã¦æ›¸ã„ã¦ã¿ã¾ã—ãŸã®ã§ã€ãŠæ™‚é–“ã‚ã‚‹ã¨ãã«æ°—軽ã«èªã‚“ã§ã„ãŸã ã‘
データサイエンティストå«ã‚€ãƒ‡ãƒ¼ã‚¿åˆ†æžè·ã®ä»•äº‹ãŒã¤ã‚‰ã„4ã¤ã®ç†ç”±ï¼šæ´‹ã®æ±è¥¿ã‚’å•ã‚ãšã¤ã‚‰ã¿ã¯åŒã˜ã‚‰ã—ã„ - 渋谷駅å‰ã§åƒãデータサイエンティストã®ãƒ–ãƒã‚°
(Image by Pixabay) æŸæ‰€ã§ãƒã‚ºã£ã¦ã„ãŸã“ã®è¨˜äº‹ã§ã™ãŒã€‚ ã‚‚ã†èªã‚“ã 瞬間ã«ã€Œã†ã‚ーã€ã“れ完全ã«æ´‹ã®æ±è¥¿ã‚’å•ã‚ãšãƒ‡ãƒ¼ã‚¿åˆ†æžæ¥ç•Œã ã¨ã©ã“ã§ã‚‚見られるã€æ¥ç•Œã¤ã‚‰ã¿ã‚ã‚‹ã‚ã‚‹ã ãªãƒ¼ã€ã¨ã„ã†æ„ŸãŒæ¹§ã„ã¦ãã¦ã€ã“ã¿ä¸Šã’ã¦ãる涙ãŒæŠ¼ã•ãˆãã‚Œã¾ã›ã‚“ã§ã—ãŸï¼ˆå˜˜ï¼‰ã€‚ã¨ã„ã†è»½å£ã¯ã•ã¦ãŠãã€å®Ÿéš›ã«ã»ã¼åŒã˜å†…容ã®æ„šç—´ã‚’USã§ãƒ‡ãƒ¼ã‚¿ã‚µã‚¤ã‚¨ãƒ³ãƒ†ã‚£ã‚¹ãƒˆã¨ã—ã¦åƒã„ã¦ã„ãŸçŸ¥äººã‹ã‚‰ã‚‚ç›´ã«èžã„ãŸã“ã¨ãŒã‚ã‚‹ã®ã§ã€å€‹äººçš„ã«ã‚‚ã‹ãªã‚Šèª¬å¾—力ã®ã‚る話ã ãªã¨æ€ã„ã¾ã—ãŸã€‚ ã“ã®è¨˜äº‹ã®è‹¥å¹²å«Œãªã¨ã“ã‚ã¯ã€Œãƒ‡ãƒ¼ã‚¿ã‚µã‚¤ã‚¨ãƒ³ãƒ†ã‚£ã‚¹ãƒˆãŸã¡ã¯ã„ã¤ã§ã‚‚転è·æ´»å‹•ã‚’ã—ã¦ã„ã‚‹ã€ä½•æ•…ãªã‚‰ã©ã“ã®è·å ´ã«è¡Œã£ã¦ã‚‚以下ã®ã¤ã‚‰ã¿ãŒã‚ã‚‹ã‹ã‚‰ã ã€ã¨ã„ã†æ›¸ã方をã—ã¦ã„る点。ã„ã‚„ã€ãƒ‡ãƒ¼ã‚¿ã‚µã‚¤ã‚¨ãƒ³ãƒ†ã‚£ã‚¹ãƒˆå«ã‚€ãƒ‡ãƒ¼ã‚¿åˆ†æžè·ãŒå…¨å“¡å¸¸ã«è»¢è·æ´»å‹•ã—ã¦ã„ã‚‹ã‹ã¨ã„ã†ã¨ã•ã™ãŒã«é•ã†ã ã‚ã†ã¨æ€ã„ã¾ã™ãŒã€ã€Œãã‚Œãらã„ã¤ã‚‰ã„ã‚“ã§ã™ãƒžã‚¸å‹˜å¼ã—ã¦ä¸‹ã•ã„ã€ã¨è¨€ã‚ã‚ŒãŸã‚‰é ·ã‹ã–ã‚‹ã‚’å¾—ãªã„ã®ã‚‚ã¾ãŸäº‹å®Ÿã‹ãª
Kaggleクレジットカードè©æ¬ºãƒ‡ãƒ¼ã‚¿ã‚»ãƒƒãƒˆã§3種ã®ç•°å¸¸æ¤œçŸ¥ã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ を比較
ã¯ã˜ã‚ã« Scutumã§ã¯2017å¹´ã®åˆæ—¬ã‹ã‚‰ã‚¢ãƒŽãƒžãƒªæ¤œçŸ¥(異常検知)ã«ã‚ˆã‚‹é˜²å¾¡æ©Ÿèƒ½ã®é–‹ç™ºã‚’æœ¬æ ¼çš„ã«ã‚¹ã‚¿ãƒ¼ãƒˆã—ã€1å¹´ã»ã©ã‹ã‘ã¦å¾ã€…ã«å®Ÿç”¨æ€§ã‚’高ã‚ã¦ãã¾ã—ãŸã€‚ã“ã“ã§è¡Œã£ã¦ã„ã‚‹ã®ã¯ã„ã‚ゆる「教師ãªã—å¦ç¿’ã«ã‚ˆã‚‹ç•°å¸¸æ¤œçŸ¥ã€ã§ã€ä¸æ ¸ã¨ã—ã¦ã„るアルゴリズムã¯XBOSã¨ã„ã†ã‚‚ã®ã§ã™ã€‚ ã—ã°ã‚‰ãã®é–“ã¯å®Œå…¨ã«æ‰‹æŽ¢ã‚Šã§ã‚·ã‚¹ãƒ†ãƒ 開発を進ã‚ã¦ã„ã¦ã€ç•°å¸¸æ¤œå‡ºã®ã‚¢ãƒ«ã‚´ãƒªã‚ºãƒ ã®å®šé‡çš„ãªæ€§èƒ½ã«ã¤ã„ã¦ã¯ç§‘å¦çš„ãªè£ä»˜ã‘ã«ä¹ã—ã„状態ã§ã—ãŸã€‚「ãªã‚“ã¨ãªãå‹•ã„ã¦ã„ã‚‹(異常を見ã¤ã‘ã‚‹ã“ã¨ãŒã§ãã¦ã„ã‚‹)よã†ã ã‹ã‚‰ã€ã“ã‚Œã§ã„ã„ã‹ã€ã¨ã„ã†æ„Ÿã˜ã®çŠ¶æ…‹ã§ãƒ‡ãƒ—ãƒã‚¤ã—ã€çµæžœã‚’見ã¦æ”¹å–„ã‚’é‡ãã‚‹ã¨ã„ã†ã‚µã‚¤ã‚¯ãƒ«ã‚’ç¹°ã‚Šè¿”ã—ã¦ããŸå½¢ã§ã™ã€‚ 2018å¹´ã«ãªã‚Šã€ã“ã‚Œã¾ã§æ®†ã©ç›®ã‚’通ã™ã“ã¨ãŒã§ãã¦ã„ãªã‹ã£ãŸç•°å¸¸æ¤œçŸ¥ã«é–¢ã™ã‚‹å¦è¡“çš„ãªæƒ…å ±(è«–æ–‡ç‰)を見ã¦ã„ãŸã¨ã“ã‚ã€ã„ãã¤ã‹é¢ç™½ã„発見ãŒã‚ã‚Šã¾ã—ãŸã€‚ãã“ã§ä»Šå›žã€å°‘ã—自分ã§ã‚‚手を動ã‹ã—ã¦èª¿æŸ»ã—ãŸãƒã‚¤ãƒ³ãƒˆã®ã†ã¡ã®1ã¤ã€3ã¤ã®
データ分æžã‚³ãƒ³ãƒ†ã‚¹ãƒˆã®â€¨å‹è€…解ç”ã‹ã‚‰å¦ã¶
ステアラボ人工知能シンãƒã‚¸ã‚¦ãƒ 2018 講演資料 https://stair.connpass.com/event/76647/
Metasploit Meets Machine Learning | MBSD Blog
Metasploit Framework（以下ã€Metasploit）ã¨ã¯ã€ãƒšãƒãƒˆãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ãƒ†ã‚¹ãƒˆã‚„脆弱性診æ–ã§ä½¿ç”¨ã•ã‚Œã‚‹ç›£æŸ»ãƒ„ールã®1ã¤ã§ã‚ã‚Šã€Port scanningã‚„Exploitã®å®Ÿè¡Œã€ãŠã‚ˆã³è„†å¼±æ€§èª¿æŸ»ã®ãŸã‚ã®æ§˜ã€…ãªè£œåŠ©ãƒ„ールãŒå«ã¾ã‚ŒãŸã‚³ãƒžãƒ³ãƒ‰ãƒ©ã‚¤ãƒ³ãƒ„ールã§ã™ã€‚ 今回ã€ç†è€…ã¯Metasploitã¨æ©Ÿæ¢°å¦ç¿’を連æºã•ã›ã€å¯¾è±¡ãƒ›ã‚¹ãƒˆã«å¯¾ã™ã‚‹æŽ¢ç´¢è¡Œç‚ºã‹ã‚‰ä¾µå…¥ã¾ã§ã‚’自動的ã«å®Ÿè¡Œã™ã‚‹ç‹¬è‡ªã®æ¤œè¨¼ãƒ„ール「Deep Exploit (beta)ã€ï¼ˆä»¥ä¸‹ã€Deep Exploit）を作æˆã—ã¾ã—ãŸã€‚本ツールを先日開催ã•ã‚ŒãŸSECCON YOROZUã«å‡ºå±•ã—ãŸã¨ã“ã‚好評を得ã¾ã—ãŸã®ã§ã€æœ¬ãƒ–ãƒã‚°ã§è¨è¨ˆæ€æƒ³ã‚„実装方法ãŠã‚ˆã³ãƒ‡ãƒ¢ã‚’ãŠè¦‹ã›ã—ã¾ã™ã€‚ ç¾æ™‚点ã®Deep Exploitã¯beta版ã§ã™ãŒã€ä»¥ä¸‹ã®è¡Œç‚ºã‚’実行å¯èƒ½ã§ã™ã€‚ Intelligence gathering 対象ホストã®æƒ…å ±ã‚’Port scanni
統計検定 1 ç´šã«åˆæ ¼ã™ã‚‹æ–¹æ³• - Qiita
Deleted articles cannot be recovered. Draft of this article would be also deleted. Are you sure you want to delete this article? ã¯ã˜ã‚ã«: 統計å¦ã®é‡è¦æ€§ NTT データ数ç†ã‚·ã‚¹ãƒ†ãƒ ã§ãƒªã‚µãƒ¼ãƒãƒ£ãƒ¼ã‚’ã—ã¦ã„る大槻 (通称ã€ã‘ã‚“ã¡ã‚‡ã‚“) ã§ã™ã€‚ 今回ã¯çµ±è¨ˆæ¤œå®š 1 ç´šã«ã¤ã„ã¦è¨˜ã—ã¾ã™ã€‚ 統計検定ã¨ã¯æ—¥æœ¬çµ±è¨ˆå¦ä¼šã«ã‚ˆã‚‹å…¬èªã®è³‡æ ¼ã§ã‚ã‚Šã€çµ±è¨ˆã«é–¢ã™ã‚‹çŸ¥è˜ã‚„活用力を評価ã™ã‚‹ã‚‚ã®ã§ã™ã€‚ 日常的ã«å¤§é‡ã®ãƒ‡ãƒ¼ã‚¿ãŒæº¢ã‚Œã¦ã„る昨今ã€ãƒ‡ãƒ¼ã‚¿åˆ†æžã‚„機械å¦ç¿’ã«å¯¾ã™ã‚‹ãƒ‹ãƒ¼ã‚ºã¯æœ€é«˜ã®é«˜ã¾ã‚Šã‚’見ã›ã¦ã„ã¾ã™ã€‚最近ã§ã¯ä½•ã‚‚考ãˆãšã¨ã‚‚ãŸã データを入力ã™ã‚‹ã ã‘ã§ãƒ‡ãƒ¼ã‚¿åˆ†æžã‚„機械å¦ç¿’手法を実行ã—ã¦ãれるツールも多数出回るよã†ã«ãªã‚Šã¾ã—ãŸã€‚ データ分æžã‚„機械å¦ç¿’を実際ã«é‚è¡Œã™ã‚‹ã«ã‚ãŸã£ã¦ã€çµ±è¨ˆå¦ã¯å¼·åŠ›ãªåŸº
Deep Learning, Structure and Innate Priors | Abigail See
Earlier this month, I had the exciting opportunity to moderate a discussion between Professors Yann LeCun and Christopher Manning, titled “What innate priors should we build into the architecture of deep learning systems?†The event was a special installment of AI Salon, a discussion series held within the Stanford AI Lab that often features expert guests. This discussion topic – about the structu
メンテナンス
ãŠçŸ¥ã‚‰ã›
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
A Proof of Useful Work for Artificial Intelligence on the Blockchain
GitHub - japan-medical-ai/medical-ai-course-materials
Papers with Code - The latest in Machine Learning
Mozilla Common Voice
http://www012.upp.so-net.ne.jp/doi/biostat/CT39/delta.pdf
Machine Learning  | Google for Developers
education#%3Fmodal_active=none
{{#tags}}- {{label}}
{{/tags}}