Linear Digressions

by Ben Jaffe and Katie Malone

In each episode, your hosts explore machine learning and data science through interesting (and often very unusual) applications.

174 Episodes

A Technical Introduction to Capsule Networks

Last episode we talked conceptually about capsule networks, the latest and greatest computer vision innovation to come out of Geoff Hinton's lab. This week we're getting a little more into the technical details, for those of you ready to have your mind stretched.

Play Download

16 April 2018 • 31 minutes

A Conceptual Introduction to Capsule Networks

Convolutional nets are great for image classification... if this were 2016. But it's 2018 and Canada's greatest neural networker Geoff Hinton has some new ideas, namely capsule networks. Capsule nets are a completely new type of neural net architecture designed to do image classification on far fewe...

Play Download

9 April 2018 • 14 minutes

Convolutional Neural Nets

If you've done image recognition or computer vision tasks with a neural network, you've probably used a convolutional neural net. This episode is all about the architecture and implementation details of convolutional networks, and the tricks that make them so good at image tasks.

Play Download

2 April 2018 • 21 minutes

Google Flu Trends

It's been a nasty flu season this year. So we were remembering a story from a few years back (but not covered yet on this podcast) about when Google tried to predict flu outbreaks faster than the Centers for Disease Control by monitoring searches and looking for spikes in searches for flu symptoms,...

Play Download

26 March 2018 • 12 minutes

How to pick projects for a professional data science team

This week's episodes is for data scientists, sure, but also for data science managers and executives at companies with data science teams. These folks all think very differently about the same question: what should a data science team be working on? And how should that decision be made? That's the s...

Play Download

19 March 2018 • 31 minutes


Autoencoders are neural nets that are optimized for creating outputs that... look like the inputs to the network. Turns out this is a not-too-shabby way to do unsupervised machine learning with neural nets.

Play Download

12 March 2018 • 12 minutes

When Private Data Isn't Private Anymore

After all the back-patting around making data science datasets and code more openly available, we figured it was time to also dump a bucket of cold water on everyone's heads and talk about the things that can go wrong when data and code is a little too open. In this episode, we'll talk about two i...

Play Download

5 March 2018 • 26 minutes

What makes a machine learning algorithm "superhuman"?

A few weeks ago, we podcasted about a neural network that was being touted as "better than doctors" in diagnosing pneumonia from chest x-rays, and how the underlying dataset used to train the algorithm raised some serious questions. We're back again this week with further developments, as the author...

Play Download

26 February 2018 • 34 minutes

Open Data and Open Science

One interesting trend we've noted recently is the proliferation of papers, articles and blog posts about data science that don't just tell the result--they include data and code that allow anyone to repeat the analysis. It's far from universal (for a timely counterpoint, read this article ), but we...

Play Download

19 February 2018 • 16 minutes

Defining the quality of a machine learning production system

Building a machine learning system and maintaining it in production are two very different things. Some folks over at Google wrote a paper that shares their thoughts around all the items you might want to test or check for your production ML system. Relevant links:

Play Download

12 February 2018 • 20 minutes