STEP BY STEP
Designing Your Neural Networks
What’s a good learning rate? How many hidden layers should your network have? Is dropout actually useful? Why are your gradients vanishing? - Towards Data Science

ADD TO CART
How Much Have You Spent on Amazon? Analyzing Amazon Data
The Director of Data Science at HelioCampus gives this tutorial gets a hearty recommendation: “This is the kind of project I mean when I talk about project-driven learning—it has relevance to you, so there's motivation to find out the answers beyond just learning a technical skill. And plenty of variations of Qs to ask.” - Dataquest

TAKE YOUR PICK
Pros and Cons of Chart Taxonomies
Chart taxonomies provide a jumping off point, but they having a list of pre-selected options could stifle innovation in data viz design. - Nightingale

CHOP CHOP
Logs Were Our Lifeblood. Now They're Our Liability.
“If the first ten years of data science were all about collecting and analyzing everything, the second ten will be about how to be deliberate and selective about collected and analyzed data.” - Normcore Tech

New from Mode

How Mode and intermix.io Deliver Fast Queries on Amazon Redshift
Identify and optimize the rogue, slow queries that are likely to knock out workflows and reports for the hundreds of dashboard users.