{"id":326469,"date":"2021-07-15T09:00:16","date_gmt":"2021-07-15T09:00:16","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=326469"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=326469","title":{"rendered":"DataScience Digest \u2014 15.07.21"},"content":{"rendered":"\n<div class=\"post__text post__text_v2\" id=\"post-content-body\">\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/7c1\/cc1\/667\/7c1cc1667051c03c3583572a519ef543.png\" width=\"1024\" height=\"512\"><figcaption><\/figcaption><\/figure>\n<p>\u0412\u0441\u0442\u0440\u0435\u0447\u0430\u0439\u0442\u0435 \u0441\u0432\u0435\u0436\u0438\u0439 \u0432\u044b\u043f\u0443\u0441\u043a&nbsp;<a href=\"https:\/\/dataphoenix.info\/tag\/digest\/\" rel=\"noopener noreferrer nofollow\">\u0434\u0430\u0439\u0434\u0436\u0435\u0441\u0442\u0430<\/a>&nbsp;\u043f\u043e\u043b\u0435\u0437\u043d\u044b\u0445 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u043e\u0432 \u0438\u0437 \u043c\u0438\u0440\u0430 Data Science &amp; Machine Learning \u0438 \u043d\u0435 \u0437\u0430\u0431\u044b\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u0434\u043f\u0438\u0441\u044b\u0432\u0430\u0442\u044c\u0441\u044f \u043d\u0430 \u043d\u0430\u0448&nbsp;<a href=\"https:\/\/t.me\/DataPhoenix\" rel=\"noopener noreferrer nofollow\"><u>Telegram-\u043a\u0430\u043d\u0430\u043b<\/u><\/a>.<\/p>\n<hr>\n<h3>\u0421\u0442\u0430\u0442\u044c\u0438<\/h3>\n<p><a href=\"https:\/\/medium.com\/pytorch\/catalyst-neuro-a-3d-brain-segmentation-pipeline-for-mri-b1bb1109276a\" rel=\"noopener noreferrer nofollow\"><strong>Catalyst.Neuro: A 3D Brain Segmentation Pipeline for MRI<\/strong><\/a> &#8212; \u043e\u0431\u0437\u043e\u0440\u043d\u0430\u044f \u0441\u0442\u0430\u0442\u044c\u044f \u043e Catalyst.Neuro, \u043d\u043e\u0432\u043e\u043c \u043f\u0430\u0439\u043f\u043b\u0430\u0439\u043d\u0435 \u0434\u043b\u044f \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u041c\u0420\u0422 \u0441\u043d\u0438\u043c\u043a\u043e\u0432 \u043c\u043e\u0437\u0433\u0430.<\/p>\n<p><a href=\"https:\/\/towardsdatascience.com\/effortless-distributed-training-of-ultra-wide-gcns-6e9873f58a50\" rel=\"noopener noreferrer nofollow\"><strong>Effortless Distributed Training of Ultra-Wide GCNs<\/strong><\/a><strong> &#8212;<\/strong> \u0441\u0442\u0430\u0442\u044c\u044f \u043e \u043d\u043e\u0432\u043e\u043c \u043f\u043e\u0434\u0442\u0438\u043f\u0435 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0432\u0435\u0440\u0442\u043e\u0447\u043d\u044b\u0445 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0435\u0442\u0435\u0439.<\/p>\n<p><a href=\"https:\/\/ai.facebook.com\/blog\/reverse-engineering-generative-model-from-a-single-deepfake-image\/\" rel=\"noopener noreferrer nofollow\"><strong>Reverse Engineering Generative Models from a Single Deepfake Image<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u043e\u0431\u043d\u0430\u0440\u0443\u0436\u0435\u043d\u0438\u044f \u0433\u043b\u0443\u0431\u043e\u043a\u0438\u0445 \u0444\u0435\u0439\u043a\u043e\u0432 \u043e\u0442 Facebook AI \u0438 \u041c\u0438\u0447\u0438\u0433\u0430\u043d\u0441\u043a\u043e\u0433\u043e \u0423\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430.<\/p>\n<p><a href=\"https:\/\/venturebeat.com\/2021\/06\/25\/overview-of-deep-learning-architectures-computers-use-to-detect-objects\/\" rel=\"noopener noreferrer nofollow\"><strong>Overview of Deep Learning Architectures Computers Use to Detect Objects<\/strong><\/a> &#8212; \u043e\u0431\u0437\u043e\u0440 \u0430\u0440\u0445\u0438\u0442\u0435\u043a\u0442\u0443\u0440 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0435\u0442\u0435\u0439, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c\u044b\u0445 \u0434\u043b\u044f \u043e\u0431\u043d\u0430\u0440\u0443\u0436\u0435\u043d\u0438\u044f \u043e\u0431\u044a\u0435\u043a\u0442\u043e\u0432.<\/p>\n<p><a href=\"https:\/\/ehoogeboom.github.io\/post\/en_flows\/\" rel=\"noopener noreferrer nofollow\"><strong>How to Build E(n) Equivariant Normalizing Flows, for Points with Features?<\/strong><\/a> &#8212;  \u043c\u0435\u0442\u043e\u0434\u044b \u0438 \u0441\u043f\u043e\u0441\u043e\u0431\u044b \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u044d\u043a\u0432\u0438\u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043d\u044b\u0445 \u043d\u043e\u0440\u043c\u0430\u043b\u0438\u0437\u0443\u044e\u0449\u0438\u0445 \u043f\u043e\u0442\u043e\u043a\u043e\u0432.<\/p>\n<p><a href=\"https:\/\/towardsdatascience.com\/read-excel-files-with-python-1000x-faster-407d07ad0ed8\" rel=\"noopener noreferrer nofollow\"><strong>Do You Read Excel Files with Python? There is a 1000x Faster Way<\/strong><\/a> &#8212; \u043c\u0435\u0442\u043e\u0434\u044b \u0443\u0441\u043a\u043e\u0440\u0435\u043d\u0438\u044f \u0440\u0430\u0431\u043e\u0442\u044b \u0441 Excel \u0444\u0430\u0439\u043b\u0430\u043c\u0438 \u0432 Python<\/p>\n<p><a href=\"https:\/\/towardsdatascience.com\/the-importance-of-layered-thinking-in-data-engineering-a09f685edc71\" rel=\"noopener noreferrer nofollow\"><strong>The Importance of Layered Thinking in Data Engineering<\/strong><\/a> -\u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u043e\u0435 \u043c\u044b\u0448\u043b\u0435\u043d\u0438\u0435 \u043f\u0440\u0438 \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0435 ML \u043f\u0430\u0439\u043f\u043b\u0430\u0439\u043d\u043e\u0432.<\/p>\n<p><a href=\"https:\/\/eng.uber.com\/elastic-xgboost-ray\/\" rel=\"noopener noreferrer nofollow\"><strong>Elastic Distributed Training with XGBoost on Ray<\/strong><\/a> &#8212; \u044d\u043b\u0430\u0441\u0442\u0438\u0447\u043d\u043e\u0435 \u0440\u0430\u0441\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u043d\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 XGBoost \u043d\u0430 Ray \u0432 Uber.<\/p>\n<p><a href=\"https:\/\/eng.uber.com\/tuning-model-performance\/\" rel=\"noopener noreferrer nofollow\"><strong>Tuning Model Performance<\/strong><\/a> &#8212; \u0441\u0442\u0430\u0442\u044c\u044f \u043e \u0442\u043e\u043c, \u043a\u0430\u043a Uber \u0441\u043e\u0437\u0434\u0430\u0435\u0442 \u0438 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0435 \u043c\u043e\u0434\u0435\u043b\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f Michelangelo.<\/p>\n<h3>\u041d\u0430\u0443\u0447\u043d\u044b\u0435 \u0441\u0442\u0430\u0442\u044c\u0438<\/h3>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2103.10702\" rel=\"noopener noreferrer nofollow\"><strong>ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u043e\u0431\u043d\u0430\u0440\u0443\u0436\u0435\u043d\u0438\u044f \u0432\u0437\u0430\u0438\u043c\u043e\u0441\u0432\u044f\u0437\u0435\u0439 \u043c\u0435\u0436\u0434\u0443 \u043f\u0440\u0435\u0434\u043c\u0435\u0442\u0430\u043c\u0438 \u0434\u043b\u044f \u0441\u0435\u0433\u043c\u0435\u043d\u0442\u0430\u0446\u0438\u0438 \u0442\u0435\u043a\u0441\u0442\u043e\u0432 \u0432 \u0432\u0438\u0434\u0435\u043e \u043f\u043e\u0442\u043e\u043a\u0430\u0445.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2106.14290\" rel=\"noopener noreferrer nofollow\"><strong>Darker than Black-Box: Face Reconstruction from Similarity Queries<\/strong><\/a> &#8212; \u043d\u0430\u0443\u0447\u043d\u0430\u044f \u0440\u0430\u0431\u043e\u0442\u0430 \u043e \u0440\u0435\u043a\u043e\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0438\u0438 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043b\u0438\u0446\u0430 \u0441 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435\u043c \u0437\u0430\u043f\u0440\u043e\u0441\u043e\u0432 \u043d\u0430 \u0441\u0445\u043e\u0434\u0441\u0442\u0432\u043e.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2107.02418\" rel=\"noopener noreferrer nofollow\"><strong>Probabilistic Graph Reasoning for Natural Proof Generation<\/strong><\/a> &#8212; \u0440\u0430\u0431\u043e\u0442\u0430 \u043e \u043d\u043e\u0432\u043e\u043c \u043c\u0435\u0442\u043e\u0434\u0435 \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u0435\u0441\u0442\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u044b\u0445 \u0434\u043e\u043a\u0430\u0437\u0430\u0442\u0435\u043b\u044c\u0441\u0442\u0432 (PRobr).<\/p>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2107.04713\" rel=\"noopener noreferrer nofollow\"><strong>Automated Graph Learning via Population Based Self-Tuning GCN<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0433\u0440\u0430\u0444\u043e\u0432 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e \u0441\u0430\u043c\u043e\u043d\u0430\u0441\u0442\u0440\u0430\u0438\u0432\u0430\u044e\u0449\u0435\u0439\u0441\u044f GCN.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2106.15397\" rel=\"noopener noreferrer nofollow\"><strong>Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelines<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u043f\u043e\u0434\u0445\u043e\u0434 \u043a \u0434\u0438\u0437\u0430\u0439\u043d\u0443 \u043a\u043e\u043c\u043f\u043e\u0437\u0438\u0442\u043d\u044b\u0445 \u041c\u041b-\u043f\u0430\u0439\u043f\u043b\u0430\u0439\u043d\u043e.<\/p>\n<h3>\u041a\u043d\u0438\u0433\u0438<\/h3>\n<p><a href=\"https:\/\/www.datascienceatthecommandline.com\/2e\/\" rel=\"noopener noreferrer nofollow\"><strong>Data Science at the Command Line, 2e<\/strong><\/a> &#8212; \u0441\u0430\u0439\u0442, \u043d\u0430 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u0432\u044b\u043a\u043b\u0430\u0434\u044b\u0432\u0430\u0435\u0442\u0441\u044f \u0447\u0430\u0441\u0442\u0438 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u043e\u0432 \u0438\u0437 \u0432\u0442\u043e\u0440\u043e\u0433\u043e \u0438\u0437\u0434\u0430\u043d\u0438\u044f \u043a\u043d\u0438\u0433\u0438 Data Science at the Command Line.<\/p>\n<h3>\u041a\u0443\u0440\u0441\u044b<\/h3>\n<p><a href=\"https:\/\/www.cs.ox.ac.uk\/people\/nando.defreitas\/machinelearning\/\" rel=\"noopener noreferrer nofollow\"><strong>Machine Learning Course from University of Oxford<\/strong><\/a><strong> <\/strong>&#8212; \u0441\u0431\u043e\u0440\u043d\u0438\u043a \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u043e\u0432 \u043a\u0443\u0440\u0441\u0430 \u043f\u043e \u041c\u041b \u043e\u0442 \u041e\u043a\u0441\u0444\u043e\u0440\u0434\u0441\u043a\u043e\u0433\u043e \u0423\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430<\/p>\n<h3>\u0414\u0430\u0442\u0430\u0441\u0435\u0442\u044b<\/h3>\n<p><a href=\"https:\/\/ai.facebook.com\/blog\/introducing-the-habitat-matterport-3d-research-data-set-for-training-embodied-ai\/\" rel=\"noopener noreferrer nofollow\"><strong>Introducing the Habitat-Matterport 3D Research Data Set for Training Embodied AI<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u0431\u043e\u043b\u044c\u0448\u043e\u0439 \u0434\u0430\u0442\u0430\u0441\u0435\u0442 \u0441 3D \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u044f\u043c\u0438 \u0436\u0438\u043b\u044b\u0445 \u043f\u043e\u043c\u0435\u0449\u0435\u043d\u0438\u0439<\/p>\n<hr>\n<p>\u0421\u043f\u0430\u0441\u0438\u0431\u043e, \u0447\u0442\u043e \u0434\u043e\u0447\u0438\u0442\u0430\u043b\u0438 \u044d\u0442\u043e\u0442 \u0432\u044b\u043f\u0443\u0441\u043a. \u041d\u0430\u0434\u0435\u044e\u0441\u044c, \u043a\u0430\u0436\u0434\u044b\u0439 \u043d\u0430\u0448\u0435\u043b \u0434\u043b\u044f \u0441\u0435\u0431\u044f \u0447\u0442\u043e-\u0442\u043e \u043f\u043e\u043b\u0435\u0437\u043d\u043e\u0435. \u0411\u0443\u0434\u0443 \u0431\u043b\u0430\u0433\u043e\u0434\u0430\u0440\u0435\u043d \u0437\u0430 \u043b\u044e\u0431\u044b\u0435 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0435\u0433\u043e \u0434\u0430\u0439\u0434\u0436\u0435\u0441\u0442\u0430.<\/p>\n<p>\u041f\u0440\u0438\u0441\u043e\u0435\u0434\u0438\u043d\u044f\u0439\u0442\u0435\u0441\u044c \u043a&nbsp;<a href=\"https:\/\/t.me\/DataPhoenix\" rel=\"noopener noreferrer nofollow\"><u>Telegram-\u043a\u0430\u043d\u0430\u043b\u0443<\/u><\/a>&nbsp;\u0434\u0430\u0439\u0434\u0436\u0435\u0441\u0442\u0430 \u0438 \u0435\u0433\u043e \u0441\u0442\u0440\u0430\u043d\u0438\u0446\u0430\u043c \u0432 \u0441\u043e\u0446\u0441\u0435\u0442\u044f\u0445:&nbsp;<a href=\"https:\/\/twitter.com\/Data_Phoenix\" rel=\"noopener noreferrer nofollow\"><u>Twitter<\/u><\/a>,&nbsp;<a href=\"https:\/\/www.facebook.com\/DataPhoenix.info\" rel=\"noopener noreferrer nofollow\"><u>Facebook<\/u><\/a>, \u0430 \u0442\u0430\u043a\u0436\u0435 \u043f\u043e\u0434\u043f\u0438\u0441\u044b\u0432\u0430\u0439\u0442\u0435\u0441\u044c \u043d\u0430 \u043d\u0430\u0448\u0443 \u0435\u0436\u0435\u043d\u0435\u0434\u0435\u043b\u044c\u043d\u0443\u044e&nbsp;<a href=\"https:\/\/dataphoenix.info\/subscribe\/\" rel=\"noopener noreferrer nofollow\">\u0440\u0430\u0441\u0441\u044b\u043b\u043a\u0443<\/a>.<\/p>\n<p>\u2190&nbsp;<a href=\"https:\/\/habr.com\/ru\/post\/566712\/\" rel=\"noopener noreferrer nofollow\">\u041f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0438\u0439 \u0432\u044b\u043f\u0443\u0441\u043a<\/a>.<\/p>\n<\/div>\n<p> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/post\/567832\/\"> https:\/\/habr.com\/ru\/post\/567832\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"\n<div class=\"post__text post__text_v2\" id=\"post-content-body\">\n<figure class=\"full-width\"><figcaption><\/figcaption><\/figure>\n<p>\u0412\u0441\u0442\u0440\u0435\u0447\u0430\u0439\u0442\u0435 \u0441\u0432\u0435\u0436\u0438\u0439 \u0432\u044b\u043f\u0443\u0441\u043a&nbsp;<a href=\"https:\/\/dataphoenix.info\/tag\/digest\/\" rel=\"noopener noreferrer nofollow\">\u0434\u0430\u0439\u0434\u0436\u0435\u0441\u0442\u0430<\/a>&nbsp;\u043f\u043e\u043b\u0435\u0437\u043d\u044b\u0445 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u043e\u0432 \u0438\u0437 \u043c\u0438\u0440\u0430 Data Science &amp; Machine Learning \u0438 \u043d\u0435 \u0437\u0430\u0431\u044b\u0432\u0430\u0439\u0442\u0435 \u043f\u043e\u0434\u043f\u0438\u0441\u044b\u0432\u0430\u0442\u044c\u0441\u044f \u043d\u0430 \u043d\u0430\u0448&nbsp;<a href=\"https:\/\/t.me\/DataPhoenix\" rel=\"noopener noreferrer nofollow\"><u>Telegram-\u043a\u0430\u043d\u0430\u043b<\/u><\/a>.<\/p>\n<hr>\n<h3>\u0421\u0442\u0430\u0442\u044c\u0438<\/h3>\n<p><a href=\"https:\/\/medium.com\/pytorch\/catalyst-neuro-a-3d-brain-segmentation-pipeline-for-mri-b1bb1109276a\" rel=\"noopener noreferrer nofollow\"><strong>Catalyst.Neuro: A 3D Brain Segmentation Pipeline for MRI<\/strong><\/a> &#8212; \u043e\u0431\u0437\u043e\u0440\u043d\u0430\u044f \u0441\u0442\u0430\u0442\u044c\u044f \u043e Catalyst.Neuro, \u043d\u043e\u0432\u043e\u043c \u043f\u0430\u0439\u043f\u043b\u0430\u0439\u043d\u0435 \u0434\u043b\u044f \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u041c\u0420\u0422 \u0441\u043d\u0438\u043c\u043a\u043e\u0432 \u043c\u043e\u0437\u0433\u0430.<\/p>\n<p><a href=\"https:\/\/towardsdatascience.com\/effortless-distributed-training-of-ultra-wide-gcns-6e9873f58a50\" rel=\"noopener noreferrer nofollow\"><strong>Effortless Distributed Training of Ultra-Wide GCNs<\/strong><\/a><strong> &#8212;<\/strong> \u0441\u0442\u0430\u0442\u044c\u044f \u043e \u043d\u043e\u0432\u043e\u043c \u043f\u043e\u0434\u0442\u0438\u043f\u0435 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0432\u0435\u0440\u0442\u043e\u0447\u043d\u044b\u0445 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0435\u0442\u0435\u0439.<\/p>\n<p><a href=\"https:\/\/ai.facebook.com\/blog\/reverse-engineering-generative-model-from-a-single-deepfake-image\/\" rel=\"noopener noreferrer nofollow\"><strong>Reverse Engineering Generative Models from a Single Deepfake Image<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u043e\u0431\u043d\u0430\u0440\u0443\u0436\u0435\u043d\u0438\u044f \u0433\u043b\u0443\u0431\u043e\u043a\u0438\u0445 \u0444\u0435\u0439\u043a\u043e\u0432 \u043e\u0442 Facebook AI \u0438 \u041c\u0438\u0447\u0438\u0433\u0430\u043d\u0441\u043a\u043e\u0433\u043e \u0423\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430.<\/p>\n<p><a href=\"https:\/\/venturebeat.com\/2021\/06\/25\/overview-of-deep-learning-architectures-computers-use-to-detect-objects\/\" rel=\"noopener noreferrer nofollow\"><strong>Overview of Deep Learning Architectures Computers Use to Detect Objects<\/strong><\/a> &#8212; \u043e\u0431\u0437\u043e\u0440 \u0430\u0440\u0445\u0438\u0442\u0435\u043a\u0442\u0443\u0440 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0435\u0442\u0435\u0439, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c\u044b\u0445 \u0434\u043b\u044f \u043e\u0431\u043d\u0430\u0440\u0443\u0436\u0435\u043d\u0438\u044f \u043e\u0431\u044a\u0435\u043a\u0442\u043e\u0432.<\/p>\n<p><a href=\"https:\/\/ehoogeboom.github.io\/post\/en_flows\/\" rel=\"noopener noreferrer nofollow\"><strong>How to Build E(n) Equivariant Normalizing Flows, for Points with Features?<\/strong><\/a> &#8212;  \u043c\u0435\u0442\u043e\u0434\u044b \u0438 \u0441\u043f\u043e\u0441\u043e\u0431\u044b \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u044d\u043a\u0432\u0438\u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043d\u044b\u0445 \u043d\u043e\u0440\u043c\u0430\u043b\u0438\u0437\u0443\u044e\u0449\u0438\u0445 \u043f\u043e\u0442\u043e\u043a\u043e\u0432.<\/p>\n<p><a href=\"https:\/\/towardsdatascience.com\/read-excel-files-with-python-1000x-faster-407d07ad0ed8\" rel=\"noopener noreferrer nofollow\"><strong>Do You Read Excel Files with Python? There is a 1000x Faster Way<\/strong><\/a> &#8212; \u043c\u0435\u0442\u043e\u0434\u044b \u0443\u0441\u043a\u043e\u0440\u0435\u043d\u0438\u044f \u0440\u0430\u0431\u043e\u0442\u044b \u0441 Excel \u0444\u0430\u0439\u043b\u0430\u043c\u0438 \u0432 Python<\/p>\n<p><a href=\"https:\/\/towardsdatascience.com\/the-importance-of-layered-thinking-in-data-engineering-a09f685edc71\" rel=\"noopener noreferrer nofollow\"><strong>The Importance of Layered Thinking in Data Engineering<\/strong><\/a> -\u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u043e\u0435 \u043c\u044b\u0448\u043b\u0435\u043d\u0438\u0435 \u043f\u0440\u0438 \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0435 ML \u043f\u0430\u0439\u043f\u043b\u0430\u0439\u043d\u043e\u0432.<\/p>\n<p><a href=\"https:\/\/eng.uber.com\/elastic-xgboost-ray\/\" rel=\"noopener noreferrer nofollow\"><strong>Elastic Distributed Training with XGBoost on Ray<\/strong><\/a> &#8212; \u044d\u043b\u0430\u0441\u0442\u0438\u0447\u043d\u043e\u0435 \u0440\u0430\u0441\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u043d\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 XGBoost \u043d\u0430 Ray \u0432 Uber.<\/p>\n<p><a href=\"https:\/\/eng.uber.com\/tuning-model-performance\/\" rel=\"noopener noreferrer nofollow\"><strong>Tuning Model Performance<\/strong><\/a> &#8212; \u0441\u0442\u0430\u0442\u044c\u044f \u043e \u0442\u043e\u043c, \u043a\u0430\u043a Uber \u0441\u043e\u0437\u0434\u0430\u0435\u0442 \u0438 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442 \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0435 \u043c\u043e\u0434\u0435\u043b\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f Michelangelo.<\/p>\n<h3>\u041d\u0430\u0443\u0447\u043d\u044b\u0435 \u0441\u0442\u0430\u0442\u044c\u0438<\/h3>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2103.10702\" rel=\"noopener noreferrer nofollow\"><strong>ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u043e\u0431\u043d\u0430\u0440\u0443\u0436\u0435\u043d\u0438\u044f \u0432\u0437\u0430\u0438\u043c\u043e\u0441\u0432\u044f\u0437\u0435\u0439 \u043c\u0435\u0436\u0434\u0443 \u043f\u0440\u0435\u0434\u043c\u0435\u0442\u0430\u043c\u0438 \u0434\u043b\u044f \u0441\u0435\u0433\u043c\u0435\u043d\u0442\u0430\u0446\u0438\u0438 \u0442\u0435\u043a\u0441\u0442\u043e\u0432 \u0432 \u0432\u0438\u0434\u0435\u043e \u043f\u043e\u0442\u043e\u043a\u0430\u0445.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2106.14290\" rel=\"noopener noreferrer nofollow\"><strong>Darker than Black-Box: Face Reconstruction from Similarity Queries<\/strong><\/a> &#8212; \u043d\u0430\u0443\u0447\u043d\u0430\u044f \u0440\u0430\u0431\u043e\u0442\u0430 \u043e \u0440\u0435\u043a\u043e\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0438\u0438 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u043b\u0438\u0446\u0430 \u0441 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435\u043c \u0437\u0430\u043f\u0440\u043e\u0441\u043e\u0432 \u043d\u0430 \u0441\u0445\u043e\u0434\u0441\u0442\u0432\u043e.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2107.02418\" rel=\"noopener noreferrer nofollow\"><strong>Probabilistic Graph Reasoning for Natural Proof Generation<\/strong><\/a> &#8212; \u0440\u0430\u0431\u043e\u0442\u0430 \u043e \u043d\u043e\u0432\u043e\u043c \u043c\u0435\u0442\u043e\u0434\u0435 \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u0435\u0441\u0442\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u044b\u0445 \u0434\u043e\u043a\u0430\u0437\u0430\u0442\u0435\u043b\u044c\u0441\u0442\u0432 (PRobr).<\/p>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2107.04713\" rel=\"noopener noreferrer nofollow\"><strong>Automated Graph Learning via Population Based Self-Tuning GCN<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0433\u0440\u0430\u0444\u043e\u0432 \u0441 \u043f\u043e\u043c\u043e\u0449\u044c\u044e \u0441\u0430\u043c\u043e\u043d\u0430\u0441\u0442\u0440\u0430\u0438\u0432\u0430\u044e\u0449\u0435\u0439\u0441\u044f GCN.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2106.15397\" rel=\"noopener noreferrer nofollow\"><strong>Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelines<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u043f\u043e\u0434\u0445\u043e\u0434 \u043a \u0434\u0438\u0437\u0430\u0439\u043d\u0443 \u043a\u043e\u043c\u043f\u043e\u0437\u0438\u0442\u043d\u044b\u0445 \u041c\u041b-\u043f\u0430\u0439\u043f\u043b\u0430\u0439\u043d\u043e.<\/p>\n<h3>\u041a\u043d\u0438\u0433\u0438<\/h3>\n<p><a href=\"https:\/\/www.datascienceatthecommandline.com\/2e\/\" rel=\"noopener noreferrer nofollow\"><strong>Data Science at the Command Line, 2e<\/strong><\/a> &#8212; \u0441\u0430\u0439\u0442, \u043d\u0430 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u0432\u044b\u043a\u043b\u0430\u0434\u044b\u0432\u0430\u0435\u0442\u0441\u044f \u0447\u0430\u0441\u0442\u0438 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u043e\u0432 \u0438\u0437 \u0432\u0442\u043e\u0440\u043e\u0433\u043e \u0438\u0437\u0434\u0430\u043d\u0438\u044f \u043a\u043d\u0438\u0433\u0438 Data Science at the Command Line.<\/p>\n<h3>\u041a\u0443\u0440\u0441\u044b<\/h3>\n<p><a href=\"https:\/\/www.cs.ox.ac.uk\/people\/nando.defreitas\/machinelearning\/\" rel=\"noopener noreferrer nofollow\"><strong>Machine Learning Course from University of Oxford<\/strong><\/a><strong> <\/strong>&#8212; \u0441\u0431\u043e\u0440\u043d\u0438\u043a \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u043e\u0432 \u043a\u0443\u0440\u0441\u0430 \u043f\u043e \u041c\u041b \u043e\u0442 \u041e\u043a\u0441\u0444\u043e\u0440\u0434\u0441\u043a\u043e\u0433\u043e \u0423\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430<\/p>\n<h3>\u0414\u0430\u0442\u0430\u0441\u0435\u0442\u044b<\/h3>\n<p><a href=\"https:\/\/ai.facebook.com\/blog\/introducing-the-habitat-matterport-3d-research-data-set-for-training-embodied-ai\/\" rel=\"noopener noreferrer nofollow\"><strong>Introducing the Habitat-Matterport 3D Research Data Set for Training Embodied AI<\/strong><\/a> &#8212; \u043d\u043e\u0432\u044b\u0439 \u0431\u043e\u043b\u044c\u0448\u043e\u0439 \u0434\u0430\u0442\u0430\u0441\u0435\u0442 \u0441 3D \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u044f\u043c\u0438 \u0436\u0438\u043b\u044b\u0445 \u043f\u043e\u043c\u0435\u0449\u0435\u043d\u0438\u0439<\/p>\n<hr>\n<p>\u0421\u043f\u0430\u0441\u0438\u0431\u043e, \u0447\u0442\u043e \u0434\u043e\u0447\u0438\u0442\u0430\u043b\u0438 \u044d\u0442\u043e\u0442 \u0432\u044b\u043f\u0443\u0441\u043a. \u041d\u0430\u0434\u0435\u044e\u0441\u044c, \u043a\u0430\u0436\u0434\u044b\u0439 \u043d\u0430\u0448\u0435\u043b \u0434\u043b\u044f \u0441\u0435\u0431\u044f \u0447\u0442\u043e-\u0442\u043e \u043f\u043e\u043b\u0435\u0437\u043d\u043e\u0435. \u0411\u0443\u0434\u0443 \u0431\u043b\u0430\u0433\u043e\u0434\u0430\u0440\u0435\u043d \u0437\u0430 \u043b\u044e\u0431\u044b\u0435 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0435\u0433\u043e \u0434\u0430\u0439\u0434\u0436\u0435\u0441\u0442\u0430.<\/p>\n<p>\u041f\u0440\u0438\u0441\u043e\u0435\u0434\u0438\u043d\u044f\u0439\u0442\u0435\u0441\u044c \u043a&nbsp;<a href=\"https:\/\/t.me\/DataPhoenix\" rel=\"noopener noreferrer nofollow\"><u>Telegram-\u043a\u0430\u043d\u0430\u043b\u0443<\/u><\/a>&nbsp;\u0434\u0430\u0439\u0434\u0436\u0435\u0441\u0442\u0430 \u0438 \u0435\u0433\u043e \u0441\u0442\u0440\u0430\u043d\u0438\u0446\u0430\u043c \u0432 \u0441\u043e\u0446\u0441\u0435\u0442\u044f\u0445:&nbsp;<a href=\"https:\/\/twitter.com\/Data_Phoenix\" rel=\"noopener noreferrer nofollow\"><u>Twitter<\/u><\/a>,&nbsp;<a href=\"https:\/\/www.facebook.com\/DataPhoenix.info\" rel=\"noopener noreferrer nofollow\"><u>Facebook<\/u><\/a>, \u0430 \u0442\u0430\u043a\u0436\u0435 \u043f\u043e\u0434\u043f\u0438\u0441\u044b\u0432\u0430\u0439\u0442\u0435\u0441\u044c \u043d\u0430 \u043d\u0430\u0448\u0443 \u0435\u0436\u0435\u043d\u0435\u0434\u0435\u043b\u044c\u043d\u0443\u044e&nbsp;<a href=\"https:\/\/dataphoenix.info\/subscribe\/\" rel=\"noopener noreferrer nofollow\">\u0440\u0430\u0441\u0441\u044b\u043b\u043a\u0443<\/a>.<\/p>\n<p>\u2190&nbsp;<a href=\"https:\/\/habr.com\/ru\/post\/566712\/\" rel=\"noopener noreferrer nofollow\">\u041f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0438\u0439 \u0432\u044b\u043f\u0443\u0441\u043a<\/a>.<\/p>\n<\/div>\n<p> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/post\/567832\/\"> https:\/\/habr.com\/ru\/post\/567832\/<\/a><br \/><\/br><\/br><\/hr>\n<\/div>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-326469","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/326469","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=326469"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/326469\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=326469"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=326469"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=326469"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}