A Technical Introduction to Capsule Networks

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 1 month ago • Duration: 31 minutes

A Conceptual Introduction to Capsule Networks

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 1 month ago • Duration: 14 minutes

Convolutional Neural Nets

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 1 month ago • Duration: 21 minutes

Google Flu Trends

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 1 month ago • Duration: 12 minutes

How to pick projects for a professional data science team

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 2 months ago • Duration: 31 minutes

Autoencoders

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 2 months ago • Duration: 12 minutes

When Private Data Isn't Private Anymore

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 2 months ago • Duration: 26 minutes

What makes a machine learning algorithm "superhuman"?

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 2 months ago • Duration: 34 minutes

Open Data and Open Science

from Linear Digressions
by Ben Jaffe and Katie Malone

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

Published 3 months ago • Duration: 16 minutes

Defining the quality of a machine learning production system

from Linear Digressions
by Ben Jaffe and Katie Malone

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: https://research.google.com/pubs/...

Play Download

Published 3 months ago • Duration: 20 minutes

Auto-generating websites with deep learning

from Linear Digressions
by Ben Jaffe and Katie Malone

We've already talked about neural nets in some detail (links below), and in particular we've been blown away by the way that image recognition from convolutional neural nets can be fed into recurrent neural nets that generate descriptions and captions of the images. Our episode today tells a similar...

Play Download

Published 3 months ago • Duration: 19 minutes

The Case for Learned Index Structures, Part 2: Hash Maps and Bloom Filters

from Linear Digressions
by Ben Jaffe and Katie Malone

Last week we started the story of how you could use a machine learning model in place of a data structure, and this week we wrap up with an exploration of Bloom Filters and Hash Maps. Just like last week, when we covered B-trees, we'll walk through both the "classic" implementation of these data str...

Play Download

Published 3 months ago • Duration: 20 minutes

The Case for Learned Index Structures, Part 1: B-Trees

from Linear Digressions
by Ben Jaffe and Katie Malone

Jeff Dean and his collaborators at Google are turning the machine learning world upside down (again) with a recent paper about how machine learning models can be used as surprisingly effective substitutes for classic data structures. In this first part of a two-part series, we'll go through a data s...

Play Download

Published 4 months ago • Duration: 18 minutes

Challenges with Using Machine Learning to Classify Chest X-Rays

from Linear Digressions
by Ben Jaffe and Katie Malone

Another installment in our "machine learning might not be a silver bullet for solving medical problems" series. This week, we have a high-profile blog post that has been making the rounds for the last few weeks, in which a neural network trained to visually recognize various diseases in chest x-rays...

Play Download

Published 4 months ago • Duration: 18 minutes

The Fourier Transform

from Linear Digressions
by Ben Jaffe and Katie Malone

The Fourier transform is one of the handiest tools in signal processing for dealing with periodic time series data. Using a Fourier transform, you can break apart a complex periodic function into a bunch of sine and cosine waves, and figure out what the amplitude, frequency and offset of those compo...

Play Download

Published 4 months ago • Duration: 15 minutes

Statistics of Beer

from Linear Digressions
by Ben Jaffe and Katie Malone

What better way to kick off a new year than with an episode on the statistics of brewing beer?

Play Download

Published 4 months ago • Duration: 15 minutes

Re - Release: Random Kanye

from Linear Digressions
by Ben Jaffe and Katie Malone

We have a throwback episode for you today as we take the week off to enjoy the holidays. This week: what happens when you have a markov chain that generates mashup Kanye West lyrics with Bible verses? Exactly what you think.

Play Download

Published 4 months ago • Duration: 9 minutes

Debiasing Word Embeddings

from Linear Digressions
by Ben Jaffe and Katie Malone

When we covered the Word2Vec algorithm for embedding words, we mentioned parenthetically that the word embeddings it produces can sometimes be a little bit less than ideal--in particular, gender bias from our society can creep into the embeddings and give results that are sexist. For example, occupa...

Play Download

Published 5 months ago • Duration: 18 minutes

The Kernel Trick and Support Vector Machines

from Linear Digressions
by Ben Jaffe and Katie Malone

Picking up after last week's episode about maximal margin classifiers, this week we'll go into the kernel trick and how that (combined with maximal margin algorithms) gives us the much-vaunted support vector machine.

Play Download

Published 5 months ago • Duration: 17 minutes

Maximal Margin Classifiers

from Linear Digressions
by Ben Jaffe and Katie Malone

Maximal margin classifiers are a way of thinking about supervised learning entirely in terms of the decision boundary between two classes, and defining that boundary in a way that maximizes the distance from any given point to the boundary. It's a neat way to think about statistical learning and a...

Play Download

Published 5 months ago • Duration: 14 minutes

Re - Release: The Cocktail Party Problem

from Linear Digressions
by Ben Jaffe and Katie Malone

Grab a cocktail, put on your favorite karaoke track, and let’s talk some more about disentangling audio data!

Play Download

Published 5 months ago • Duration: 13 minutes

Clustering with DBSCAN

from Linear Digressions
by Ben Jaffe and Katie Malone

DBSCAN is a density-based clustering algorithm for doing unsupervised learning. It's pretty nifty: with just two parameters, you can specify "dense" regions in your data, and grow those regions out organically to find clusters. In particular, it can fit irregularly-shaped clusters, and it can also...

Play Download

Published 6 months ago • Duration: 16 minutes

The Kaggle Survey on Data Science

from Linear Digressions
by Ben Jaffe and Katie Malone

Want to know what's going on in data science these days?  There's no better way than to analyze a survey with over 16,000 responses that recently released by Kaggle.  Kaggle asked practicing and aspiring data scientists about themselves, their tools, how they find jobs, what they find challenging ab...

Play Download

Published 6 months ago • Duration: 25 minutes

Machine Learning: The High Interest Credit Card of Technical Debt

from Linear Digressions
by Ben Jaffe and Katie Malone

This week, we've got a fun paper by our friends at Google about the hidden costs of maintaining machine learning workflows. If you've worked in software before, you're probably familiar with the idea of technical debt, which are inefficiencies that crop up in the code when you're trying to go fast....

Play Download

Published 6 months ago • Duration: 22 minutes
0:00/0:00