- PVSM.RU - https://www.pvsm.ru -
Добрый день! Это второй дайджест материалов по машинному обучению и анализу данных. Несмотря на праздники на этой неделе было много интересного.
События предстоящей недели
1. Семинар СМиГО [1]: Multi-Class Classification: How to Deal with Multi-class Huge Scale Problems Efficiently? 28 февраля.
2. Data science завтрак [2]. 1 марта.
3. Superjob Data Science Meetup [3]. 2 марта.
4. Open & Big Data Hackathon 2017 [4]. г. Санкт-Петербург. 3 марта.
5. Data Science Weekend [5]. 3 марта.
6. Moscow Data Science meetup [6]. 3 марта.
7. День открытых данных в Москве [7]. 4 марта.
Учебные курсы, конференции
1. На Физтехе стартует курс “Дополнительные главы машинного обучения” [8].
2. ML-тренировка. DeepHack RL, Avito BI [9]. Видео.
3. Диалоговые интерфейсы: проблемы и вызовы [10]. Видео.
4. NIPS 2016 Workshop on Adversarial Training [11]. Декабрьская конференция в Барселоне. Видео.
5. Deep Learning Summer School and Reinforcement Learning Summer School [12].
Новости
1. Лаборатория Касперского проведет хакатон [13] по анализу данных.
2. Еженедельный обзор от DataScienceCentral [14].
3. Еженедельный обзор портала HighScalability [15].
4. GPUs are now available for Google Compute Engine and Cloud Machine Learning [16].
Научные статьи, практические реализации, датасеты
1. Pachyderm: A Containerized, Version-Controlled Data Lake [17].
2. Базовые принципы машинного обучения на примере линейной регрессии [18].
3. TensorFlow Quick Tips [19].
4. Predicting gentrification using longitudinal census data [20].
5. How is Deep Learning Changing Data Science Paradigms? [21]
6. Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks [22].
7. Управление публичными данными [23].
8. High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis [24].
9. How to train Baidu's Deepspeech model with Kur [25].
10. Semantic Question Matching with Deep Learning [26].
11. Combining neural networks and decision trees [27].
12. Char2Wav: End-to-End Speech Synthesis [28].
13. Fast PixelCNN++: speedy image generation [29].
14. Intro and preprocessing — Using Convolutional Neural Network to Identify Dogs vs Cats. Часть 1 [30]. Часть 2 [31]. Часть 3 [32]. Часть 4 [33]. Видео.
15. Lots of labeled and annotated data [34]
16. Эвристическая сеть — аналог рекуррентной нейронной сети для программы чат бот [35].
17. Brain Trust: How AI Is Helping Surgeons Improve Tumor Diagnosis [36].
18. Ranking every Data Science course on the internet [37].
19. Data Manipulation and Visualization with Pandas and Seaborn — A Practical Introduction [38].
20. Interactive Image Translation with pix2pix-tensorflow [39].
21. Обучение с подкреплением: от Павлова до игровых автоматов [40].
22. PixelNet: Representation of the pixels, by the pixels, and for the pixels [41].
23. Learning to generate one-sentence biographies from Wikidata [42].
24. How to Difference a Time Series Dataset with Python [43].
25. Нейронные сети: практическое применение [44].
26. How to Make a Tensorflow Image Classifier [45]. Видео.
27. Introduction to Neural Networks — Perceptron [46].
28. Recognizing Traffic Lights With Deep Learning [47].
29. Serve Spark ML Models Using Play Framework and S3 [48].
30. The Black Magic of Deep Learning — Tips and Tricks for the practitioner [49].
31. RBM based Autoencoders with tensorflow [50].
32. Social Media Research Toolkit [51].
33. Нейронные сети в картинках: от одного нейрона до глубоких архитектур [52].
34. Neural Network Learns to Synthetically Age Faces, and Make Them Look Younger, Too [53].
35. How to Save an ARIMA Time Series Forecasting Model in Python [54].
36. How to Create a Linux Virtual Machine For Machine Learning Development With Python 3 [55].
37. Beginner's Guide to Customer Segmentation [56].
38. Bare bones Python implementations of some of the foundational Machine Learning models and algorithms [57].
39. Announcing Prophet: A tool that provides accurate, reliable forecasting [58].
40. Butterfly effect: OECD’s data visualisation hiccup leads to media panic [59].
41. Preprocessing for Machine Learning with tf.Transform [60].
42. Умная кормушка: Machine Learning, Raspberry Pi, Telegram, немножко магии обучения + инструкция по сборке [61].
43. High-Res-Neural-Inpainting — High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis [24].
Предыдущий выпуск: Обзор материалов по машинному обучению (13 — 20 февраля 2017 года) [62].
Автор: Alf162
Источник [63]
Сайт-источник PVSM.RU: https://www.pvsm.ru
Путь до страницы источника: https://www.pvsm.ru/analiz-danny-h/246673
Ссылки в тексте:
[1] Семинар СМиГО: https://calendar.google.com/calendar/render?eid=MHR2ZGZqdHEwa2lodmJwMmJyNmVydTl1aW8gb2xuOGowcTI0cm04aTVoMGEwYnVrYjVmdjBAZw&sf=true&output=xml#eventpage_6
[2] Data science завтрак: https://calendar.google.com/calendar/render?eid=NmdwamlkMWc2aGltMmJiMmM4c2phYjlrNzBzajZiOW9jNWlqOGJiNTZ0aGplZGo1Y2dxM2NwMzVjY18yMDE3MDMwMVQwNjMwMDBaIG9sbjhqMHEyNHJtOGk1aDBhMGJ1a2I1ZnYwQGc&sf=true&output=xml#eventpage_6
[3] Superjob Data Science Meetup: https://calendar.google.com/calendar/render?eid=MGZrMGprM2dsbWZ0ajVidmRmb3RuMW1vNmMgb2xuOGowcTI0cm04aTVoMGEwYnVrYjVmdjBAZw&sf=true&output=xml#eventpage_6
[4] Open & Big Data Hackathon 2017: https://calendar.google.com/calendar/render?eid=b3ZxbWxhNnRqOTN2dDFuM3VjbjU3dTQyOWcgb2xuOGowcTI0cm04aTVoMGEwYnVrYjVmdjBAZw&sf=true&output=xml#eventpage_6
[5] Data Science Weekend: https://calendar.google.com/calendar/render?eid=bGgyNHI0ajBhbXZsdWtjazhrYXNqZWM3aTAgb2xuOGowcTI0cm04aTVoMGEwYnVrYjVmdjBAZw&sf=true&output=xml#eventpage_6
[6] Moscow Data Science meetup: https://calendar.google.com/calendar/render?eid=OGlxOGVrZm8yYmhob3VzcTJuNHBpMjZzcTAgb2xuOGowcTI0cm04aTVoMGEwYnVrYjVmdjBAZw&sf=true&output=xml#eventpage_6
[7] День открытых данных в Москве: https://calendar.google.com/calendar/render?eid=c210MDhzamVnaDM0NTMyOXRzcGFoNHN0NG8gb2xuOGowcTI0cm04aTVoMGEwYnVrYjVmdjBAZw&sf=true&output=xml#eventpage_6
[8] “Дополнительные главы машинного обучения”: http://phystech-union.org/2017/02/17/machinelearningcourse/
[9] ML-тренировка. DeepHack RL, Avito BI: https://www.youtube.com/watch?v=h35u_T7p5tU&feature=youtu.be
[10] Диалоговые интерфейсы: проблемы и вызовы: https://youtu.be/gYTTlb4bORk
[11] NIPS 2016 Workshop on Adversarial Training: https://www.youtube.com/playlist?list=PLJscN9YDD1buxCitmej1pjJkR5PMhenTF
[12] Deep Learning Summer School and Reinforcement Learning Summer School: https://mila.umontreal.ca/en/cours/deep-learning-summer-school-2017/
[13] Лаборатория Касперского проведет хакатон: https://events.kaspersky.com/hackathon/?utm_source=kaspercareer1
[14] Еженедельный обзор от DataScienceCentral: http://www.datasciencecentral.com/profiles/blogs/weekly-digest-february-27
[15] Еженедельный обзор портала HighScalability: http://highscalability.com/blog/2017/2/19/stuff-the-internet-says-on-scalability-for-february-17th-201.html
[16] GPUs are now available for Google Compute Engine and Cloud Machine Learning: https://cloudplatform.googleblog.com/2017/02/GPUs-are-now-available-for-Google-Compute-Engine-and-Cloud-Machine-Learning.html
[17] Pachyderm: A Containerized, Version-Controlled Data Lake: https://github.com/pachyderm/pachyderm
[18] Базовые принципы машинного обучения на примере линейной регрессии: https://habrahabr.ru/company/ods/blog/322076/
[19] TensorFlow Quick Tips: http://www.deeplearningweekly.com/blog/tensorflow-quick-tips
[20] Predicting gentrification using longitudinal census data: http://urbanspatialanalysis.com/portfolio/predicting-gentrification-using-longitudinal-census-data/?utm_content=buffer326bc&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer
[21] How is Deep Learning Changing Data Science Paradigms?: http://bytes.schibsted.com/deep-learning-changing-data-science-paradigms/
[22] Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks: https://arxiv.org/pdf/1702.05870.pdf
[23] Управление публичными данными: https://habrahabr.ru/post/322150/
[24] High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis: https://github.com/leehomyc/High-Res-Neural-Inpainting
[25] How to train Baidu's Deepspeech model with Kur: http://blog.deepgram.com/how-to-train-baidus-deepspeech-model-with-kur/
[26] Semantic Question Matching with Deep Learning: https://engineering.quora.com/Semantic-Question-Matching-with-Deep-Learning
[27] Combining neural networks and decision trees: https://github.com/nenadmarkus/nets-and-trees
[28] Char2Wav: End-to-End Speech Synthesis: http://josesotelo.com/speechsynthesis/
[29] Fast PixelCNN++: speedy image generation: https://github.com/PrajitR/fast-pixel-cnn
[30] Часть 1: https://www.youtube.com/watch?v=gT4F3HGYXf4
[31] Часть 2: https://www.youtube.com/watch?v=Ge65ukmJTzQ
[32] Часть 3: https://www.youtube.com/watch?v=ViO56ASqeks
[33] Часть 4: https://www.youtube.com/watch?v=27FPv1VHSsQ
[34] Lots of labeled and annotated data: https://medium.com/startup-grind/fueling-the-ai-gold-rush-7ae438505bc2#.8ag050lwa
[35] Эвристическая сеть — аналог рекуррентной нейронной сети для программы чат бот: https://habrahabr.ru/post/322346/
[36] Brain Trust: How AI Is Helping Surgeons Improve Tumor Diagnosis: https://blogs.nvidia.com/blog/2017/02/17/ai-helps-improve-brain-tumor-diagnosis/
[37] Ranking every Data Science course on the internet: https://medium.freecodecamp.com/i-ranked-all-the-best-data-science-intro-courses-based-on-thousands-of-data-points-db5dc7e3eb8e#.wl9y9ti73
[38] Data Manipulation and Visualization with Pandas and Seaborn — A Practical Introduction: https://gist.github.com/5agado/ee95008f25730d04bfd0eedd5c36f0ee#file-pandas-and-seaborn-ipynb
[39] Interactive Image Translation with pix2pix-tensorflow: http://affinelayer.com/pixsrv/
[40] Обучение с подкреплением: от Павлова до игровых автоматов: https://habrahabr.ru/post/322404/
[41] PixelNet: Representation of the pixels, by the pixels, and for the pixels: https://arxiv.org/abs/1702.06506
[42] Learning to generate one-sentence biographies from Wikidata: https://arxiv.org/pdf/1702.06235.pdf
[43] How to Difference a Time Series Dataset with Python: http://machinelearningmastery.com/difference-time-series-dataset-python/
[44] Нейронные сети: практическое применение: https://habrahabr.ru/post/322392/
[45] How to Make a Tensorflow Image Classifier: https://www.youtube.com/watch?v=APmF6qE3Vjc&feature=em-lss
[46] Introduction to Neural Networks — Perceptron: https://www.neuraldesigner.com/blog/perceptron-the-main-component-of-neural-networks
[47] Recognizing Traffic Lights With Deep Learning: https://medium.freecodecamp.com/recognizing-traffic-lights-with-deep-learning-23dae23287cc#.swix4g2vo
[48] Serve Spark ML Models Using Play Framework and S3: https://commitlogs.com/2017/02/18/serve-spark-ml-model-using-play-framework-and-s3/
[49] The Black Magic of Deep Learning — Tips and Tricks for the practitioner: https://nmarkou.blogspot.ru/2017/02/the-black-magic-of-deep-learning-tips.html
[50] RBM based Autoencoders with tensorflow: https://ikhlestov.github.io/posts/rbm-based-autoencoders-with-tensorflow/
[51] Social Media Research Toolkit: http://socialmediadata.org/social-media-research-toolkit/
[52] Нейронные сети в картинках: от одного нейрона до глубоких архитектур: https://habrahabr.ru/post/322438/
[53] Neural Network Learns to Synthetically Age Faces, and Make Them Look Younger, Too: https://www.technologyreview.com/s/603684/neural-network-learns-to-synthetically-age-faces-and-make-them-look-younger-too/
[54] How to Save an ARIMA Time Series Forecasting Model in Python: http://machinelearningmastery.com/save-arima-time-series-forecasting-model-python/
[55] How to Create a Linux Virtual Machine For Machine Learning Development With Python 3: http://machinelearningmastery.com/linux-virtual-machine-machine-learning-development-python-3/
[56] Beginner's Guide to Customer Segmentation: http://blog.yhat.com/posts/customer-segmentation-python-rodeo.html
[57] Bare bones Python implementations of some of the foundational Machine Learning models and algorithms: https://github.com/eriklindernoren/ML-From-Scratch
[58] Announcing Prophet: A tool that provides accurate, reliable forecasting: https://research.fb.com/prophet-forecasting-at-scale/
[59] Butterfly effect: OECD’s data visualisation hiccup leads to media panic: http://datawanderings.com/2017/02/23/butterfly-effect/
[60] Preprocessing for Machine Learning with tf.Transform: https://research.googleblog.com/2017/02/preprocessing-for-machine-learning-with.html?m=1
[61] Умная кормушка: Machine Learning, Raspberry Pi, Telegram, немножко магии обучения + инструкция по сборке: https://habrahabr.ru/post/322520/
[62] Обзор материалов по машинному обучению (13 — 20 февраля 2017 года): https://habrahabr.ru/post/322188/
[63] Источник: https://habrahabr.ru/post/322660/?utm_source=habrahabr&utm_medium=rss&utm_campaign=best
Нажмите здесь для печати.