[in case you missed it] Data Science Weekly - Issue 245
Issue #245 Aug 2 2018
Editor Picks
Hiring for Autonomy in Data Science Teams
In our latest episode of the In Context Podcast, we're joined by Eric Colson, the Chief Algorithms Officer for Stitch Fix, an online subcription personal shopping service whose tech blog, Multithreaded, may have the coolest algorithms tour on the internet. In a fascinating discussion, he and Kathryn Hume analyze how Stitch Fix's engineering culture works, including what they value, what they look for in new hires, and how they’ve architected their platform to enable astounding success. You'll also hear about the critical role that autonomy plays in how Eric organizes his data science teams...
Keras implementation of Image OutPainting
Implementation of Painting Outside the Box: Image Outpainting paper...
Data-mining medieval text reveals medically bioactive ingredients
Medieval apothecaries used recipes with significant antibacterial properties, researchers say...
A Message from this week's Sponsor:
Find A Data Science Job Through Vettery
Vettery specializes in tech roles and is completely free for job seekers. Interested? Submit your profile, and if accepted onto the platform, you can receive interview requests directly from top companies growing their data science teams. Get started.
Data Science Articles & Videos
Embrace the noise: A case study of text annotation for medical imaging
In this post we’ll discuss the recent paper TextRay: Mining Clinical Reports to Gain a Broad Understanding of Chest X-rays focusing on the best practices the paper exemplifies with regards to labeling text data for NLP...
Good First Impressions According to Data Science
Making a good first impression is hard. I made a model that can predict how good of an impression you are making based on a video clip submission...
Ten Techniques Learned From fast.ai
Right now, Jeremy Howard – the co-founder of fast.ai – currently holds the 105th highest score for the plant seedling classification contest on Kaggle, but he's dropping fast. Why? His own students are beating him. And their names can now be found across the tops of leaderboards all over Kaggle....
L1: Tensor Studio — A playground for tensor computations
An in-browser live-programming environment for differentiable tensor computations (written on top of TensorFlow.js)...
AI-driven robot hand spent a hundred years teaching itself to rotate a cube
A reinforcement-learning algorithm allows Dactyl to learn physical tasks by practicing them in a virtual-reality environment...
When Recurrent Models Don't Need to be Recurrent
We explore the trade-offs between recurrent and feed-forward models...
Using Uncertainty to Interpret your Model
Why uncertainty estimates are important in DL; Which types of uncertainty exist (data, model, measurement, label); Examples of how we can use uncertainty to interpret our model, and how we can use it for debugging...
Deep Reinforcement Learning: Playing CartPole through Asynchronous Advantage Actor Critic (A3C) with tf.keras and eager execution
In this tutorial we will learn how to train a model that is able to win at the simple game CartPole using deep reinforcement learning. We’ll use tf.keras and OpenAI’s gym to train an agent using a technique known as Asynchronous Advantage Actor Critic (A3C)...
Jobs
Data Scientist (Product) - Spotify - NYC
We are looking for a Data Scientist to join the band and help drive a data-first culture across Spotify. As a Data Scientist, our mission is to turn terabytes of data into insights and get a deep understanding of how our people use our apps to impact the product, strategy and direction of Spotify. You will study user behavior, strategic initiatives, content, and new features and bring data and insights into every decision we make. Above all, your work will impact the way the world experiences music...
Training & Resources
Multiply Two Matrices Using TensorFlow MatMul
Learn how to multiply two matricies by using TensorFlow's matmul operation, via a screencast video and full tutorial transcript...
The Hitchiker's Guide to PyTorch
The rest of this document, based on the official MNIST example, is about grokking PyTorch, and should only be looked at after the official beginner tutorials. For readability, the code is presented in chunks interspersed with comments, and hence not separated into different functions/files as it would normally be for clean, modular code...
Deep Learning: Which Loss and Activation Functions should I use?
The purpose of this post is to provide guidance on which combination of final-layer activation function and loss function should be used in a neural network depending on the business goal...
Books
Guesstimation: Solving the World's Problems on the Back of a Cocktail Napkin "Guesstimation enables anyone with basic math and science skills to estimate virtually anything--quickly--using plausible assumptions and elementary arithmetic"...
For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page.
P.S., Want to reach our audience / fellow readers? Consider sponsoring - grab a spot now; first come first served! All the best, Hannah & Sebastian