Data Science Weekly - Issue 235
Issue #235 May 24 2018
Editor Picks
Categorizing Listing Photos at Airbnb
Large-scale deep learning models are changing the way we think about images of homes on our platform...
Imaginary Soundscape
This neural net will generate a soundscape to go with wherever in Google Maps you happen to be viewing...
Does the brain store information in discrete or analog form?
New evidence in favor of a discrete form of data storage could change the way we understand the brain and the devices we build to interface with it...
A Message from this week's Sponsor:
Become an expert data scientist with the 365 Data Science Program - the only comprehensive online data science program.
All the resources you need to become a professional data scientist in one place – from the fundamentals of Mathematics, Excel, Probability, Statistics, Intro to Data & Data Science, through Tableau, SQL, R, Python, all the way up to Machine & Deep Learning.
46 hours of on-demand video, 13 courses, 336 exercises, 25 assignments.
Beautifully animated videos; real-life business examples; verifiable certificate; no previous data science background needed; full support along the way; takes weeks to complete and at a fraction of the cost of traditional degrees. Now 92% off.
Data Science Articles & Videos
hello tensorflow
Are you curious about using Machine Learning in the browser? I took a basic TensorFlow.js example, put a neat graph on it and commented every line of code, so you can play with it!!...
Deep Convolutional Neural Networks as Models of the Visual System: Q&A
Fifteen questions and answers about the use of convolutional neural networks as a model of the visual system...
Generative Ramen: jirou interpolation video
Example video from Kenji Doi features visual transitions of Japanese cuisine, generated using the same neural network framework that generated new celebrity faces...
Self-Attention Generative Adversarial Networks
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks...
Russian Natural Language Processing
Testing Russian word vectors by considering how well they represent vodka...
Into a Textual Heart of Darkness
Going zero to not-quite-hero in NLP via hate speech classification...
Using LDA Topic Modeling to Investigate the Discourse on Mental Health
For this project I set out to investigate the contexts in which ‘mental health’ has been brought up over time. For this purpose, I collected ~30k New York Times articles from the 80s to present to analyze using topic modeling....
Standardizing a Machine Learning Framework for Applied Research –
PyTorch vs MXNet
Until now, the Machine Learning (ML) frameworks we’ve used at Borealis AI have varied according to individual preference. But as our applied team grows, we’re finding that a preference-based system has certain shortcomings that have led to inefficiencies and delays in our research projects. As a result, we identified two main arguments in favour of standardizing a single framework for the lab...
Jobs
Data Scientist - SQUAD - NYC
SQAD LLC is on the cutting edge of digital and traditional, media cost measurement and forecasting. Recognized as an industry pioneer, SQAD’s data and systems serve the some of the biggest brands in media. SQAD provides reliable media cost data to advertising agencies, media buying companies, advertisers, television and radio stations, cable companies, program syndicators and Internet publishers.
What you’ll do: You will be part of a talented Dev-Ops team that is responsible for designing and developing cloud-based data solutions utilizing best-of-breed open source tools and data technologies...
Training & Resources
Create A PyTorch Identity Matrix
Learn how to create a PyTorch identity matrix by using the PyTorch eye operation, via a screencast video and full tutorial transcript...
Rules of Machine Learning - Best Practices for ML Engineering
This document is intended to help those with a basic knowledge of machine learning get the benefit of Google's best practices in machine learning. It presents a style for machine learning, similar to the Google C++ Style Guide and other popular guides to practical programming. If you have taken a class in machine learning, or built or worked on a machine-learned model, then you have the necessary background to read this document...
Fashion-MNIST with tf.Keras
This is a tutorial of how to classify the Fashion-MNIST dataset with tf.keras, using a Convolutional Neural Network (CNN) architecture. In just a few lines of code, you can define and train a model that is able to classify the images with over 90% accuracy, even without much optimization...
Books
The Theory That Would Not Die:
How Bayes' Rule Cracked the Enigma Code, Hunted Down Russian Submarines, and Emerged Triumphant from Two Centuries of Controversy An enjoyable account of the history of Bayesian statistics from Thomas Bayes's first idea to the ultimate (near-)triumph of Bayesian methods in modern statistics...
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