The world’s leading publication for data science, AI, and ML professionals.

Weekly Selection – Oct 12, 2018

Entropy is a measure of uncertainty

By Sebastian Kwiatkowski – 9 min read

Suppose you are talking with three patients in the waiting room of a doctor’s office. All three of them have just completed a medical test which, after some processing, yields one of two possible results: the disease is either present or absent.


The 4 Convolutional Neural Network Models That Can Classify Your Fashion Images

By James Le – 12 min read

Clothes shopping is a taxing experience. My eyes get bombarded with too much information. Sales, coupons, colors, toddlers, flashing lights, and crowded aisles are just a few examples of all the signals forwarded to my visual cortex, whether or not I actively try to pay attention.


How to Data Science without a Degree

By Jason Jung – 7 min read

I want to show you how to become a Data Scientist / Machine Learning Engineer without a degree (or for free). Ironically, I do have a degree – one that was even made for Data Science (Master’s in Analytics from Northwestern).


Large-scale Graph Mining with Spark

By Win Suen – 8 min read

If you’re an engineer, you’ve most likely used graph data structures for implementing search and lookups algorithms. Have you also used them for machine learning problems?


How Taxis Arrive at Fares? – Predicting New York City Yellow Cab Fares

By Susan Li – 5 min read

Predicting taxi fare is definitely not as flourishing as predicting airline fares. However, since we do not currently have airline fare open data available, why not start practicing from predicting taxi fare?


How to make a gif map using Python, Geopandas and Matplotlib

By Benjamin Cooley – 7 min read

As a language, Python is enormously flexible. Which makes it possible to make lots of different visualisations in, at times, only a few lines of code. But with all the different charting websites and software available now, why bother writing code?


An Intuitive Explanation of Policy Gradient – Part 1: REINFORCE

By Adrien Lucas Ecoffet – 13 min read

This is part 1 of a series of tutorials which I expect to have 2 or 3 parts. The next part will be on A2C and, time providing, I hope to complete a part on various forms of off-policy policy gradients.


Your Ultimate Guide to Matplotlib

By Julia Kho – 6 min read

This article is a compilation of common questions and answers on how to customize your Matplotlib plots. This serves as a great cheat sheet for speedy Matplotlib plotting and not as an introduction to the Matplotlib library.


Collaborative Embeddings for Lipstick Recommendations

By Sylvain Truong – 10 min read

For an e-commerce company, spending time and effort in the understanding of customer behaviour is a win-win strategy for both its customers and the company itself.


Stop Installing Tensorflow using pip for performance sake!

By Michael Nguyen – 2 min read

Stop installing Tensorflow using pip! Use conda instead. If you don’t know what conda is, it’s an open source package and environment management system that runs cross-platform.


Related Articles