|
|
June 24 · Issue #19 · View online
A weekly digest of all the best Data Science related news and blog posts.
|
|
Welcome to this week’s installment of my curated list of all the best data science related news and blog posts. Turning knowledge darkness into light since 2018. 🌃🌙🌞 – Luis de Sousa
|
|
Anti-symmetric
|
|
Handling Strings with R
This free book aims to provide a panoramic perspective of the wide array of string manipulations that you can perform with R.
|
Factfulness: Ten Reasons We're Wrong About the World and Why Things Are Better Than You Think by Hans Rosling
If you don’t know who Hans Rosling was, check out one of his TED talks here. This book is such a great read even Bill Gate said it is one of the most important books he’s ever read. “When asked simple questions about global trends–what percentage of the world’s population live in poverty; why the world’s population is increasing; how many girls finish school–we systematically get the answers wrong.” In this book the authors offers a radical new explanation of why this happens.
|
Hands-On Reinforcement Learning with Python - Sudharsan Ravichandiran
Master reinforcement learning and deep reinforcement learning by building intelligent applications using OpenAI, TensorFlow, and Python. Python notebooks can be found here.
|
|
Detecting unconscious bias in models, with R
Discussion of a vignette created by Paige Bailey for the ROpenSci conference, “Ethical Machine Learning: Spotting and Preventing Proxy Bias”.
|
Interpreting machine learning models with the lime package for R
Many types of machine learning classifiers are notoriously difficult to interpret. If the model produces a surprising label for any given case, it’s difficult to explain. One approach to this dilemma is the technique known as LIME (Local Interpretable Model-Agnostic Explanations).
|
How to Do Distributed Deep Learning for Object Detection Using Horovod on Azure
This blog post explains how to do distributed deep learning using Horovod on Azure. A RetinaNet object detector is trained on the COCO dataset, with distributed training enabled through Horovod and Batch AI.
|
AI Lab: Learn to Code with the Cutting-Edge Microsoft AI Platform
This blog post covers the launch of AI Lab – a collection of AI projects designed to help developers explore, experience, learn about and code with the latest Microsoft AI Platform technologies.
|
How we are fixing our installer for Microsoft R Open on Linux
Details on how Microsoft fixed the installer for Microsoft R Open on Linux.
|
|
Microsoft Research Open Data
Microsoft has released a collection of free data sets in areas such as natural language processing, computer vision, and domain-specific areas.
|
|
Better Video Impersonations with AI
The paper “Deep Video Portraits” is available here.
|
Curiosity-Driven AI: How Effective Is It?
The paper “Curiosity-driven Exploration by Self-supervised Prediction” and its source code is available here.
|
NVIDIA's AI Removes Objects From Your Photos
The paper “Image Inpainting for Irregular Holes Using Partial Convolutions” is available here.
|
Neural Image Stitching And Morphing
The paper “Neural Best-Buddies: Sparse Cross-Domain Correspondence” is available here.
|
Using transfer learning to address label noise for large-scale image classification
The paper “CleanNet: Transfer learning for scalable image classifier training with label noise” is available here.
|
Believing is seeing: Insightful research illuminates the newly possible in the realm of natural and synthetic images
The paper “CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training” is available here.
|
|
DevOps for Data Science
Learn more about what’s important to Data Scientists and where to start when it comes to a DevOps process.
|
|
facebookresearch/DensePose
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body. Link to the paper here.
|
|
Thanks for reading. As always, let us know if you have any questions or suggestions, just hit reply, click the thumbs up or thumbs down icons below or send us an email at luisd@syeop.co.za. xoxo
|
Did you enjoy this issue?
|
|
|
|
In order to unsubscribe, click here.
If you were forwarded this newsletter and you like it, you can subscribe here.
|
|
Johannesburg, South Africa, 2020
|