Hello everyone!

DataScience Digest is now on ProductHunt! Are you amazed? If so, make sure to check out us there.

Here's the link: https://www.producthunt.com/posts/datascience-digest.

Any feedback and comments are appreciated. So, let us know what you want to change or improve.

Top 8 trends from ICLR 2019: http://bit.ly/2W2i7Lq

PyTorch internals

This post is a long-form essay version of a talk about PyTorch internals by Edward Z. Yang that he gave at the PyTorch NYC meetup on May 14, 2019.

http://bit.ly/2HWXHJX

Real-time object detection part 1: Understanding SSD

This post explains the inner workings of the Single-Shot MultiBox Detector and provides a detailed code walkthrough.

http://bit.ly/2W3qWEV

​​AI Conference Kyiv 2019

On June 4, Smile-Expo will organize the second AI Conference in Kyiv – a major event dedicated to the integration of AI in business. Presentations from speakers, successful cases, smart products, and networking – the event will become a place to gain experience from the specialists who have been using AI technologies in their operations.

The conference will feature 3 theme blocks:
1. AI and machine learning.
2. IoT and data analysis.
3. Automation and chatbots.

The event will end with a roundtable dedicated to successful business development using AI, Machine Learning and IoT.

Attendees: developers, marketers, managers, analysts, and everyone who wants to improve their business with the help of AI technologies.

Tickets with a discount: a promo code AIPR20 provides a 20% discount on tickets. Enter the promo code on the registration page.

Website: https://bit.ly/2HDbUgm

InterpretML

InterpretML is an open-source package from Microsoft for training interpretable models and explaining blackbox systems.

http://bit.ly/2WbF52M

Data Science Cheatsheets:
- Artificial Intelligence
- Big Data Analytics
- Big Data
- Data Engineering
- Data Mining
- Data Science
- Data Visualization
- Deep Learning
- Machine Learning
- SQL
- Python
- etc

http://bit.ly/2I3MgQQ

How to Deploy Machine Learning Models

In this article, you will learn how to deploy machine learning models into production. It's relatively high-level, but there are links throughout to go deeper. Includes a discussion of the complexities involved, design considerations, tooling, testing, developments to watch, etc.

http://bit.ly/2KfLYcu

Artificial Intelligence cheatsheets for Stanford’s CS 221

This repository sums up all the important stuff covered in Stanford’s CS 221 Artificial Intelligence course, and includes:
— Cheatsheets for each field of artificial intelligence
— All elements of the above combined in the ultimate compilation of concepts to have at hand all the time.

http://bit.ly/2Wzazzs

AUTOML: METHODS, SYSTEMS, CHALLENGES

This open access book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects denoscriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems.

http://bit.ly/2WEdB5q

The Best and Most Current of Modern Natural Language Processing

A useful collection of resources to catch up on the latest trends in natural language processing. In addition to selected research papers, this article includes links to introductory posts, recommended blogs, online courses, and books.

http://bit.ly/2KngeBZ

​​June 11 Kyiv is going to host AWS Dev Day! Are you all fired up?

This international conference for techies is part of the global series of AWS Dev Day events, featuring three major tracks:
— Analytics & Machine Learning
— Backends & Architecture
— Modern App Development

Among all of that, the participants will attend ten keynotes delivered by strong AWS pros, engage with AWS architects at the Ask an Architect session, and visit the fabled Cost Optimization Booth.

The keynotes will be of value to Machine Learning Engineers, Data Scientists, DevOps Engineers, Solution Architects, Software Engineers, and everyone interested in the AWS ecosystem.

When: Tuesday, June 11, 9 AM — 5 PM
Where: Mercure Congress Centre

The participation is free: http://bit.ly/2KvMqn9

Testing TensorFlow Lite image classification model

In this post, we will demonstrate major differences between TensorFlow, TensorFlow Lite and quantized TensorFlow Lite (with post-training quantization) models. This should help you with early models debugging when something goes really wrong.

http://bit.ly/2WFAdmg

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

Samsung’s research center at Moscow has developed a new AI that can create talking avatars of photos and paintings without using any 3D modeling. According to the study, the system creates realistic virtual talking heads through applying the facial landmarks of a target face onto a source face -- for example, a still photo -- to allow the target face to control how the source face moves.

Paper: http://bit.ly/2QSK6Yx
Video: http://bit.ly/2QNtUHJ

Deep Learning Boot Camp

Video recordings of presentations from Deep Learning Boot Camp, which was held from 28 to 31 May in Berkeley

http://bit.ly/2QW5tbr

Time Series Forecasting with TensorFlow.js

In this article, you will learn how to pull stock prices from online API and perform predictions using Recurrent Neural Network & Long Short Term Memory (LSTM) with TensorFlow.js framework.

http://bit.ly/2QSb0PU

Initializing neural networks

Initialization can have a significant impact on convergence in training deep neural networks. Simple initialization schemes can accelerate training, but they require care to avoid common pitfalls. In this post, we’ll explain how to initialize neural network parameters effectively.

http://bit.ly/2WVBBkA

Create TensorFlow Name Scopes For TensorBoard

Use TensorFlow Name Scopes (tf.name_scope) to group graph nodes in the TensorBoard web service so that your graph visualization is legible.

http://bit.ly/2QWAvjc

ICLR 2019 posters

For those who weren’t at ICLR and want to browse the papers that were presented there, this is for you; it lets you check out many of the posters from the official ICLR poster session. In the future, founders plan to publish poster sessions from other top machine learning conferences too.

http://bit.ly/2R0m8KY

End-to-End Object Detection for Furniture Using Deep Learning

In this article, you will learn how to build an object detection algorithm using a CNN-based algorithm called “You Only Look Once” to identify, classify, and localize different types of furniture in images and videos.

http://bit.ly/2R4gPKn

16 OpenCV Functions to Start your Computer Vision journey (with Python code)

In this article, you will learn about OpenCV library and basic functions: Reading, Writing and Displaying Images, Changing Color Spaces, Resizing Images, Image Rotation, Image Translation, Simple Image Thresholding, Adaptive Thresholding, Image Segmentation (Watershed Algorithm), Bitwise Operations, Edge Detection, Image Filtering, Image Contours, Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Feature Matching, Face Detection.

http://bit.ly/2R8Dsx3