— In the News —
Toronto is one of the key AI centers in the world but over the past few years, startups and young AI researchers have been lured to tech centers like Silicon Valley. Canada wants to bring them home.
— Tools and Techniques —
Deriving value from data isn't always successful and, in fact, well-meaning efforts often fail. In this post, Brian Balfour describes the four phases of data death spirals and how to break free. The key problems? They're probably not what you think.
We often think of optimization with momentum as a ball rolling down a hill. This isn't wrong, but there is much more to the story. This interactive article is from the new Distill publication and even if you're not interested in the topic, it's really an impressive experience.
When your data changes, how will you know? assertr is an R package to help you identify common dataset errors. More specifically, it helps you spell out your assumptions about how the data should look and alert you of any deviation from those assumptions.
Here's a well-organized introduction to the machine learning landscape.
— Deep Learning —
The essence of machine learning is recognizing patterns within data. This boils down to 3 things: data, software and math. What can be done in seven lines of code you ask? A lot.
Practical advice for exploring novel applications in deep learning. This guide is intended for people who are experts in their particular field but are novices in deep learning.
— Data Viz —
Tad's a free desktop application that's designed for data people. It's free and offers a variety of features including pivot tables and a built-in SQLite database for speed and flexibility. This initial release is only available for Mac but it definitely looks promising.
Giorgia Lupi sees beauty in data. In this TED talk, she shares how we can bring personality to data, visualizing even the mundane details of our lives and transforming the abstract into something that can be seen, felt and directly reconnected to our lives.