Linear Digressions

Shapley values in machine learning are an interesting and useful enough innovation that we figured hey, why not do a two-parter? Our last episode focused on explaining what Shapley values are: they de...

13 Maj 201819min

As machine learning models get into the hands of more and more users, there's an increasing expectation that black box isn't good enough: users want to understand why the model made a given prediction...

7 Maj 201827min

If you were a machine learning researcher or data scientist ten years ago, you might have spent a lot of time implementing individual algorithms like decision trees and neural networks by hand. If you...

30 Apr 201815min

A huge part of the ascent of deep learning in the last few years is related to advances in computer hardware that makes it possible to do the computational heavy lifting required to build models with ...

23 Apr 201812min

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 technic...

16 Apr 201831min

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 ...

9 Apr 201814min

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 ...

2 Apr 201821min

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 Cent...

26 Mars 201812min