Data Science Weekly - Issue 203
Issue #203 Oct 12 2017
Editor Picks
Phone-Powered AI Spots Sick Plants with Remarkable Accuracy
Researchers have developed a smartphone-based program that can automatically detect diseases in the cassava plant—the most widely grown root crop on Earth—with darn near 100 percent accuracy. It’s a glimpse at a future in which farmers in the developing world trade the expertise of a handful of specialists for increasingly omnipresent and powerful technology...
First Evidence That Online Dating Is Changing the Nature of Society
Dating websites have changed the way couples meet. Now evidence is emerging that this change is influencing levels of interracial marriage and even the stability of marriage itself...
No order left behind; no shopper left idle.
Using Monte Carlo simulations to balance supply & demand in a marketplace (at Instacart)...
A Message from this week's Sponsor:
Attend the Future Labs AI Summit in NYC on October 30 – 31
Two days of technical trainings and talks from leading executives at Google, NASA, Vector Institute, NYU, AI4ALL, and more. Day 1 courses will be taught by experts from Intel, Amazon Web Services (AWS), Insight Data Science, Paperspace, and NYU, and include courses such as intro to machine learning and deep learning, machine learning for statisticians, and building and deploying deep learning models on AWS. Day 2 presentations will cover investing in AI, democratizing AI, the current state of quantum computing, social and ethical impacts of the technology, and more. Sign up before prices rise on October 25!
Data Science Articles & Videos
Behind the Magic: How we built the ARKit Sudoku Solver
A few weeks ago my company, Hatchlings, released Magic Sudoku for iOS11. It’s an app that solves sudoku puzzles using a combination of Computer Vision, Machine Learning, and Augmented Reality. Many people have asked me about the app so I thought it would be fun to share some behind the scenes of how and why we built it...
What you need to know before you board the machine learning train
This post is not about math or statistics, rather practical everyday advice for your next machine learning project. Hopefully by the end, you will be able to understand and appreciate scenarios where machine learning creates value...
Visualizing gender and race inequality in newsrooms
Our latest project in the collaboration with Google News Lab is an exploration of gender and race in U.S news publications. It was designed by Polygraph based on data from the American Society of News Editors (ASNE,) which has also published an article about it...
#RecSys2017 summaries and reviews
Every year after RecSys, our community takes the time to reflect and write summaries and reviews of the conference. Whether you could not make it to the conference, or you missed a session, it is always a good idea to keep an eye on what others are thinking. Here goes the list of all the #RecSys2017 summaries published so far...
Exploring Visual Motifs in Wes Anderson Films
A visual essay on image similarity in Wes Anderson films via deep learning...
GANs are Broken in More than One Way: The Numerics of GANs
Last year, when I was on a mission to "fix GANs" I had a tendency to focus only on what the loss function is, and completely disregard the issue of how do we actually find a minimum. Here is the paper that has finally challenged that attitude...
Interactions in fraud experiments: A case study in multivariable testing
A while ago we observed something curious when we ran a set of simultaneous A/B tests around multiple antifraud features. These tests were to improve our passengers’ ride payment experience and our ability to collect fares to pay our drivers. The features centered around the temporary authorization hold we use to determine if a passenger has enough money for a Lyft ride...
Inside Vicarious, the Secretive AI Startup Bringing Imagination to Computers
By reinventing the neural network, the company hopes to help computers make the leap from processing words and symbols to comprehending the real world...
Jobs
Data Scientist - MealPal - New York Are you passionate about helping an organization make smart decisions in order to deliver the best product and user experience? Do you want to join a fast-paced, growing company? As a Data Scientist at MealPal, you will focus on using data to drive business strategy and take our company to the next level. You will have the opportunity to think critically and problem solve in order to drive valuable and executable insights...
Training & Resources
TensorFlow Lattice: Flexibility Empowered by Prior Knowledge
Today we present TensorFlow Lattice, a set of prebuilt TensorFlow Estimators that are easy to use, and TensorFlow operators to build your own lattice models...
Learning Diverse Skills via Maximum Entropy Deep Reinforcement Learning
Maximum Entropy Deep Reinforcement Learning...
3Blue1Brown
A channel about animating math. Check out the "Recommended" playlist for some thought-provoking one-off topics, and take a look at the "Essence of linear algebra" for some more student-focussed material...
Books
Statistics Done Wrong: The Woefully Complete Guide "... a pithy, essential guide to statistical blunders in modern science that will show you how to keep your research blunder-free..."
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. We've just opened up booking for November & December - grab a spot now; first come first served! Email us for more details - All the best, Hannah & Sebastian