September 13, 2020

Dear friends,

Welcome to the 68th issue of the Sunday Briefing.

The latest post in the Causality series is now out. This week we consider the concept of d-separation, the fundamental tool in understanding how to make any pair of variables conditionally dependent or independent . As always, all the relevant code can be found in GitHub. You can also checkout the latest in the Epidemic Modeling series where we go over the basics of Network Structure, Superspreaders and Contact Tracing.

In our regularly scheduled content, we have a tutoral on Bidirectional LSTM on IMDB, a discussion of Why Bayesian Stats Needs Monte-Carlo Methods and an introruction on how to Automate Machine Learning with TPOT.

On the academic front, we have surveys on how to Learn from Very Few Samples, and news recommender systems a review on Networks beyond pairwise interactions and DeepSpeed, a new toll by microsoft to democratize model training.

Finaly, in the video of the week, we have a tutorial on Data Structures, the fundamental building blocks for efficient data representation in algorithms.

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