October 18, 2020

Dear friends,
Welcome to the October 18 issue of the Sunday Briefing.

The past few days were heavily focused on Causal Inference. On Monday, our blog post on Model Testing and Causal Search was kindly retweeted by Judea Pearl himself and on Friday we held the first edition of the Why and What If – Causal Analysis for Everyone webinar to an enthusiastic audience and we’re already thinking about when to schedule the next session.

We also have a new blog from the Causality series, where we dive into Chapter 3 of the Primer to learn more about Interventions, the way in which we modify the values of the variables in our model to simulate a Randomized Controled Trial. As always, all the relevant code can be found in GitHub. On the Epidemic Modeling front, you can also checkout the latest blog post where we go over the basics of Network Structure, Superspreaders and Contact Tracing.

This week, we look at how Physicists are working towards making Fairer AI by Peering Inside Its Black Box, have some deep thoughts on Cognition, quickly review consensus protocols and learn how to Use Quasi-experiments and Counterfactuals to Build Great Products.

On the academic front, we learn about Neural Databases, Zero Knowledge Games, Filtering Statistics on Networks and how LSTMs Compose (and Learn) Bottom-Up.

Finaly, in the video of the week, we have a lecture on Attention and Transformer Networks by Pascal Poupart from the University of Waterloo.

Data shows that the best way for a newsletter to grow is by word of mouth, so if you think one of your friends or colleagues would enjooy this newsletter, just go ahead and forward this email to them. This will help us spread the word!

Semper discentes,

The D4S Team