A Hands-On Introduction to Deep Q-Learning using OpenAI Gym in Python

This article will help you to take your first steps into the world of deep reinforcement learning. We’ll use one of the most popular algorithms in RL, deep Q-learning, to understand how deep RL works. We will implement all learnt in an awesome case study using Python.

http://bit.ly/2ReUZEc

​​June 18 Moscow is going to host AWS Dev Day! Are you all fired up?

What Is AWS Dev Day Moscow?
AWS Dev Day Moscow is a free, full-day technical event launched by Amazon Web Services as part of their global series of AWS Dev Day events. At the event, IT professionals and developers can learn the latest trends in the cloud and strengthen their AWS skills.

Why Is AWS Dev Day Moscow Worth Visiting?
Ten strong tech luminaries who are ready to share their knowledge and expertise; two tracks diving deep into the cloud and AWS products; «Ask an AWS Architect» sessions where every attendee can speak with AWS Architects, and more!

Among other keynotes, it’s worth noting a few: «Machine learning with Amazon SageMaker», «Containers CI/CD Pipeline on AWS», «Service Mesh Magic», «Everything as a Code: Two Years with AWS ECS in Production», «Best Practices for Integrating Amazon Rekognition into Your Own Applications», and more.

When?
Thursday, June 18, 9 AM — 5 PM

Where?
«Vesna» space, 2c1 Spartakovsky L, 7 drive

The participation is free, yet you need to register using the link below:
http://bit.ly/2XLte8z

Learn more: http://bit.ly/2XLtep5

A practical guide to Deep Learning in 6 months

This post offers a detailed roadmap to how you can learn Deep Learning well enough to get a Deep Learning internship as well as a full-time job within 6 months. This post is practical, result oriented and follows a top-down approach. It is aimed for beginners strapped for time, as well as for intermediate practitioners.

http://bit.ly/2IhKwVE

Machine Learning and Data Science Applications in Industry

A curated list of applied machine learning and data science notebooks and libraries across different industries.

http://bit.ly/2XNmvLt

The Third Wave Data Scientist

A long-awaited update of the data science skill portfolio

http://bit.ly/2IkKEDF

Pythia for vision and language multimodal AI models

Pythia is a deep learning framework that supports multitasking in the vision and language domain. Built on our open-source PyTorch framework, the modular, plug-and-play design enables researchers to quickly build, reproduce, and benchmark AI models. Pythia is designed for vision and language tasks, such as answering questions related to visual data and automatically generating image captions.

http://bit.ly/2Y132ah

​​Data Science Digest readers can get over 20% off on any RE•WORK Summit using code DSDIGEST. Meet with Bengio, Goodfellow and more https://bit.ly/2JXpWfb

Generalized Additive Models in R

This short course will teach you how to use these flexible, powerful tools to model data and solve data science problems. GAMs offer a middle ground between simple linear models and complex machine-learning techniques, allowing you to model and understand complex systems.

http://bit.ly/2InqoRO

Deep Learning Models

A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks. This collection has been up for about two weeks and has ~7,000 stars already!

http://bit.ly/2IrofEK

18 Impressive Applications of Generative Adversarial Networks

This post offers a review of a large number of interesting applications of GANs to help you develop an intuition for the types of problems where GANs can be used and useful.

http://bit.ly/31K35JI

Machine learning datasets

A list of the biggest datasets for machine learning from across the web. Computer vision, natural language processing, audio, and medical datasets.

http://bit.ly/2Fp9q3P

​​
Optimizing your R code – a guided example

Optimizing R code is not always the priority. But when you run out of memory, or it just takes too long, you start to wonder if there are better ways to do things! In this article, the author demonstrates the methods of optimizing R code and the process behind it.

http://bit.ly/2ZFvH4O

Distributed Deep Learning Pipelines with PySpark and Keras

An easy approach to data pipelining using PySpark and doing distributed deep learning with Keras.

http://bit.ly/2ZFao3s

Machine Learning for Everyone

The best general intro article about Machine Learning. Only real-world problems, practical solutions, simple language, and no high-level theorems. One and for everyone.

http://bit.ly/2ZGQBRd

Collection of Interactive Machine Learning Examples

Seedbank is a registry and search engine for Colab notebooks for machine learning, enabling rapid exploration and learning. You can browse the site and use, experiment with, and fork Colab notebooks. The forked notebooks are stored in your Google Drive and you can share them just like any other Google Docs.

http://bit.ly/2ZPFWDE

Random Forest vs AutoML

In this article, the author demonstrates how to prepare the data and train the Random Forest model on an Adult dataset with python and scikit-learn. Using the same dataset, he shows how to train Random Forest with AutoML using mljar-supervised.

http://bit.ly/2Ygkmb9

TensorWatch

TensorWatch is a debugging and visualization tool designed for data science, deep learning and reinforcement learning from Microsoft Research. It works in Jupyter Notebook to show real-time visualizations of your machine learning training and perform several other key analysis tasks for your models and data.

http://bit.ly/2YhR8ZG

And Voilà!

In this article, you will learn how Voilà turns Jupyter notebooks into standalone web applications.

http://bit.ly/2YnB74m

​​Webinar «Kubeflow, MLFlow, and Beyond — Augmenting ML Delivery»

Organized in collaboration with #ODSC, this free webinar will provide insights on how to design a reference machine learning workflow, as well as an overview of open source tools used to automate ML workflow.

The attendees will go away with a deeper view of traps and pitfalls they may come across at every stage of ML lifecycle and get a reference implementation and automation of ML Workflow.

When: July 16, 1 pm — 2 pm EST
Speaker: Stepan Pushkarev, CTO of Provectus

Act fast to register: http://bit.ly/MLFlowWebinar
Learn more: https://www.facebook.com/events/1183366371834820

PyTorch Image Models

This repository contains PyTorch image models, noscripts, pre-trained weights: (SE) ResNet/ResNeXT, DPN, EfficientNet, MobileNet-V3/V2/V1, MNASNet, Single-Path NAS, FBNet, and more.

http://bit.ly/2YlZwqW