Hello friends!
We know that some of you didn’t have the opportunity to be present at our second webinar "The A-Z of Data: Monitoring ML Models in Production". We posted the whole footage that you can check out on our website. Listen carefully, take notes, and don’t miss our future events!
https://bit.ly/3tk0owu

📌How to Detect, Evaluate, and Visualize Historical Drifts in the Data

Analyzing historical drift in data is a nice way of understanding how your data changes, to choose monitoring thresholds. Check out this tutorial for details.
https://bit.ly/3yOeEPb

Friends! Don't forget to subscribe to our weekly newsletter, a new issue is coming tomorrow! Fill in your email and get instant access to all the AI/ML goodies in one go. Looking forward to having you as one of our amazing subscribers!
https://bit.ly/3haZNby

💡Accelerating Materials Discovery with Bayesian Optimization and Graph Deep Learning

The authors show that Bayesian optimization with symmetry constraints using a graph deep learning energy model can be used to perform "DFT-free" relaxations of crystal structures.
https://bit.ly/3tnSIti

Hey friends! Today is a great day, because Data Phoenix just published the latest issue of the digest! And it is already waiting for you on our website! Tap on the link and feel free to subscribe 👇🏻
https://bit.ly/3ld7G1H

📌Complete Guide to A/B Testing Design, Implementation and Pitfalls

In this guide, the author covers a wide range of topics on end-to-end A/B testing for your Data Science experiments, with examples and Python implementation.
https://bit.ly/3E28krb

A small reminder that the Data Phoenix Events team invites you all on September 16 to our "The A-Z of Data" webinars.
The topic — re-usable pipelines for ML projects with DVC
Our speaker is Rozhkov Mikhail - Solution Engineer at Iterative.ai. ML Engineer and enthusiast with over six years of experience in Machine Learning and Data Science. Co-creator ML REPA, author of courses on automating ML experiments with DVC and MLOps. As a member of the Iterative.ai team, he helps teams improve ML development and automate MLOps processes. For more info check 👉🏻
https://bit.ly/3C1OD18

💡Annotate and Improve Computer Vision Datasets with CVAT and FiftyOne

This post covers two example workflows showing how to use the integration between FiftyOne and CVAT, helping you to build efficient annotation workflows and train better models.

https://bit.ly/3tBbEVE

​​Good morning folks! Here's your dose of positivity for this Sunday!🤗
https://bit.ly/3txuEUZ

📌Deep Reinforcement Learning at the Edge of the Statistical Precipice

In the paper, the authors propose a new approach to the reliable evaluation of deep RL models. They illustrate their findings using a case study on the Atari 100k benchmark.
https://bit.ly/3nvEiGJ

💡IKEA ASM Dataset

The IKEA ASM dataset is a multi-modal and multi-view video dataset of 371 samples of assembly tasks to enable rich analysis and understanding of human activities.
https://bit.ly/3npxg6f

📌Understanding Convolutions on Graphs

In this article, you'll learn about the building blocks and design choices of graph neural networks. Make sure to check out the Supplementary Material section for more goodies.
https://bit.ly/3EeCY0H

Friends the webinar is really soon and we hope to see you there. September 16 - "The A-Z of Data" webinars.
The topic — re-usable pipelines for ML projects with DVC.

For more info and registration tap the link 👉🏻
https://bit.ly/3tS1i3T

💡The Natural Scenes Dataset

The Natural Scenes Dataset (NSD) is a large-scale fMRI dataset consisting of whole-brain, high-resolution fMRI measurements of 8 healthy adult subjects while they viewed thousands of color natural scenes over the course of 30–40 scan sessions.
https://bit.ly/2XrEXht

The Data Phoenix Events invites you all on September 29 to our «The A-Z of Data» webinars. The topic — Pachyderm in production: lessons learned.

In this talk, we will take a look at yet another MLOps tool — Pachyderm. This tool is gaining in popularity and is unique for some use-cases. The speaker will share the experience of applying Pachyderm to a real-world, BigData NLP project. Most importantly, we will see the hidden limitations of Pachyderm and why it’s not quite the tool it claims to be.

Speaker
Oleh Lokshyn is a Machine Learning Architect at SoftServe. He built ML workflows on GCP, Azure, and on-premises for different supervised and unsupervised models. Oleh holds several certifications: Google Cloud Professional Machine Learning Engineer, Google Cloud Professional Data Engineer, Microsoft Certified Azure Data Scientist Associate.

Participation is free, but pre-registration is required.

Friends! Tomorrow we will publish the new issue of our digest, don't miss it! Fill in your email and get instant access to all the AI/ML goodies in one go. Looking forward to having you as one of our amazing subscribers!
https://bit.ly/3zdT0Ev

📢 Мы в эфире. Начинаем Open Data Science Odessa Meetup #4. Будем говорить про то, как NLP поменялся за последние 10 лет, а также про опыт участия в ML соревнованиях. Присоединяйтесь!
https://bit.ly/3zexfEz

📌Understanding ROC Curves with Python

In this article by Lucas Soares, you'll learn how to design and build the basic intuition for receiver operating characteristics (ROC) curve with Python.
https://bit.ly/3Emjes3

📢 Мы в эфире. Начинаем вебинара "Re-usable pipelines for ML projects with DVC", на котором поговорим про DVC и переиспользование ML пайплайнов между проектами.. Присоединяйтесь!
https://bit.ly/2VNfoH5

💡Simulating Traffic Flow in Python

Predicting traffic is a challenging task with multiple variables. In this article, you'll explore the methods of simulating traffic by implementing a microscopic traffic model.
https://bit.ly/3zfJuAr