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

Weekly Selection – Feb 1, 2019

Learn Enough Docker to be Useful (Part 1, Part 2, Part 3, Part 4)

By Jeff Hale – 12 min read

Containers are hugely helpful for improving security, reproducibility, and scalability in software development and data science. Their rise is one of the most important trends in technology today.


Interactive Controls in Jupyter Notebooks

By Will Koehrsen – 6 min read

There are few actions less efficient in data exploration than re-running the same cell over and over again, each time slightly changing the input parameters.


Learning to Drive Smoothly in Minutes

By Antonin RAFFIN – 11 min read

In this post, we will see how to train an autonomous racing car in minutes and how to smooth its control.


What is AI bias?

By Cassie Kozyrkov – 4 min read

The AI bias trouble starts – but doesn’t end – with definition. "Bias" is an overloaded term which means remarkably different things in different contexts.


Using Data to Find the Angriest Death Grips Song

By Evan Oppenheimer – 11 min read

Death Grips is an experimental hip hop band that has been releasing innovative, interesting, and, frankly, difficult music since 2011.


Unmaking Graphs

By Chris Crawford – 6 min read

I have the pleasure of looking at a lot of graphs (a lot) and I’ve come to learn a thing or two about which ones make the most sense.


Handling imbalanced datasets in machine learning

By Baptiste Rocca – 15 min read

Suppose that you are working in a given company and you are asked to create a model that, based on various measurements at your disposal, predicts whether a product is defective or not.


Mario vs. Wario – round 2: CNNs in PyTorch and Google Colab

By Eryk Lewinson – 9 min read

Since quite some time I was getting round to playing with Google Colab (yes, free access to GPU…).


Visualising Machine Learning Datasets with Google’s FACETS

By Parul Pandey – 8 min read

An open source tool from Google to easily learn patterns from large amounts of data


Related Articles