How to Use Polynomial Feature Transforms for Machine Learning

In this tutorial, you will discover how to use polynomial feature transforms for feature engineering with numerical input variables.

https://bit.ly/3h3dUy8

Catalyst 101 — Accelerated PyTorch

In this post, you will learn about Catalyst framework, developed with focus on reproducibility, fast experimentation, and code/idea reusing.

https://bit.ly/2Yah4r7

Using AI to predict retinal disease progression

In this post, you will learn about AI system that can predict the development of exAMD which was created by DeepMind in collaboration with Moorfields Eye Hospital and Google Health.

https://bit.ly/2MEbnwv

How to Do Data Exploration for Image Segmentation and Object Detection

In this article, the author will share with you how he approaches data exploration for image segmentation and object detection problems.

https://bit.ly/3cL9IQf

Data Science Digest (June 2020)

Hi folks, I’m happy to share with you the latest Data Science Digest issue featuring Data Science & Machine Learning goodies for June 2020. Please upvote on Habr and applaud on Medium.

Habr (RU) — https://bit.ly/30lGGUR
Medium (EN) — https://bit.ly/3f4xbNS

The Ultimate Guide to Deploying Machine Learning Models

This multi-part series is a great resource for learning about model deployment. Covers a variety of topics, including common pitfalls, interfaces, model registries, A/B testing and more.

https://bit.ly/3cNSGB3

OpenCV Social Distancing Detector

In this tutorial, you will learn what social distancing is and how OpenCV and deep learning can be used to implement a social distancing detector.

https://bit.ly/2ULzAWb

Anti-Patterns in NLP (8 types of NLP idiots)

In this talk, you will learn about common anti-patterns that happen in the industry while solving text problems.

https://bit.ly/31SwxQf

Interactive, Scalable Dashboards with Vaex and Dash

Vaex and Dash are open-source libraries that make it easy to build interactive dashboards on the web for millions, and even billions, of data samples using just your Python skills. This tutorial shows what you can do with these libraries and how to use them.

https://bit.ly/2Otifxr

​​Deep Learning with PyTorch

Download a free copy of the full book and learn how to get started with AI / ML development using PyTorch. This book provides a detailed, hands-on introduction to building and training neural networks with PyTorch, a popular open-source machine learning framework.

https://bit.ly/3jPFMqY

Understanding coordinate systems and DICOM for deep learning medical image analysis

Multiple introductory concepts regarding deep learning in medical imaging, such as coordinate system and DICOM data extraction from the machine learning perspective.

https://bit.ly/3hSi0sB

Awesome GPT-3

This evolving GPT-3 collection includes links to some of the best demos and tutorials around the web. This is a great rabbit hole for anyone interested in understanding how GPT-3 works and where it's going.

https://bit.ly/30LQozy

Object Detection from 9 FPS to 650 FPS in 6 Steps

This article is a practical deep dive into making a specific deep learning model (Nvidia’s SSD300) run fast on a powerful GPU server, but the general principles apply to all GPU programming. The SSD300 is an object-detection model trained on COCO, so output will be bounding boxes with probabilities for 81 classes of object.

https://bit.ly/34YwqTd

​​The 2020 Data & AI Landscape

In this post, you will learn about:
— Key trends in data infrastructure
— Key trends in analytics & enterprise AI
— The 2020 landscape
— Who’s in, who’s out — noteworthy IPOS, M&A and additions

https://bit.ly/378UCol

Using reinforcement learning to personalize AI-accelerated MRI scans

Our early experiments with the fastMRI data set show that our models outperform the previous active MRI acquisition state of the art over a broad range of acceleration factors.

https://bit.ly/3j1tOsz

Putting ML in Production

A guide and case study on MLOps for software engineers, data scientists and product managers. Deploy ML to production for a real product with live data using open source tools.

https://bit.ly/2GXFb89

Stanford MLSys Seminar Series

In this seminar series, we want to take a look at the frontier of machine learning systems, and how machine learning changes the modern programming stack. Our goal is to help curate a curriculum of awesome work in ML systems to help drive research focus to interesting questions.

https://stanford.io/3dFVl1J

#dataset
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation

MSeg is a composite dataset that unifies semantic segmentation datasets from different domains. In this dataset, authors reconcile the taxonomies and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images.

https://bit.ly/2Hfqc9A

Druid - Interactive Analytics At Scale

Druid – один из полезных и популярных инструментов в мире Больших Данных. Именно эта OLAP система позволяет эффективно обрабатывать, хранить и запрашивать данные. Что и подтверждает востребованность Druid среди инструментов в среде обработки Больших Данных
С Владимиром Иордановым мы поговорим о том, как работает Druid, из чего он состоит и каковы его возможности. Владимир познакомит нас с компонентами Druid, расскажет об архитектуре кластера, о том как проходит обработка данных. Мы сможем понаблюдать на практике, как с ним работать.

О спикере:
🔸 Владимир Иорданов – BigData Tech Lead в Lohika и уже более шести лет работает в проектах, связанных с Большими Данными. Его последний проект был непосредственно связан с Apache Druid. Во время работы на этом проекте Владимир получил большой опыт работы с поддержкой и разработкой под эту систему в production. Этим опытом наш спикер и поделится на BigData Odesa #TechTalks .

🔹Где: онлайн
🔹Когда: 17.12.2020 в 19:00
🔹Язык доклада: русский
🔹Регистрация обязательна
🔹Вход: donation. Будем вам признательны за перечисление любой комфортной для Вас суммы в благотворительный фонд “Корпорация монстров”. Способы перечисления помощи есть на странице регистрации.

Регистрация на онлайн-трансляцию => https://docs.google.com/forms/d/e/1FAIpQLSdALs-5FgvDKwoAVqJkbvYKOR0UTLrWTvMszDUGl1HIylISrA/viewform

Как всегда, вас ждет интересная тема и полезный вечер. Вы научитесь эффективно применять Druid в своих проектах при построении системы обработки больших данных.

Присоединяйтесь!

Hey folks!

I know, I know… You’ve all been wondering for quite a while if this digest is actually dead or kinda not exactly. I’m here to say that it’s alive and kicking, and I’m — finally — back.

Now, it makes sense to explain where I’ve been all this time. Well, I have two words for you: Covid-19 and a child (probably shouldn’t use these in one sentence).

With quarantines imposed, most people had to sit at home and watch TV series… But it wasn’t and isn’t the case if you’re a developer. Just WFH, baby. And to the babies — my son was born in May 2020, so my plate was extra full.

Anyway, the situation has stabilized, and I’m back. So, what can you expect to see next?
- Daily updates on all things AI/ML/Data on Telegram and other social media
- Weekly email newsletter with Top AI news and resources
- Quizzes and surveys
- Webinars
- Fun stuff
- etc

I hope this sorted things out a bit. Stay tuned and have a great one, all!

P. S. Updates will start arriving soon.

Best regards,
Dmitry Spodarets
@DataScienceDigest

Recommendation Algorithms & System Designs of YouTube, Spotify, Airbnb, Netflix, TikTok, and Uber

Ever wondered how top technology companies can so accurately predict their customers’ next step? Go no further! In this article, you will find a collection of recommendation algorithms and system designs that they may be using. Note that the author collected all the info from open sources and judges from his personal experience; there is no guarantee that the designs are 100% correct.

https://bit.ly/3m0y0Mo

@DataScienceDigest