A weekly newsletter with the latest developments in Data Science and Machine Learning and Artificial Intelligence.
Welcome to a very special 128th issue of the Sunday Briefing.
We continue on our hiatus from blogging, but while we prepare the next post, you can catch up on Network Assortativity and the Configurational Model where we explore Degree-Degree Correlations in the airline network. Over at the V4Sci substack you’ll find Geographical Maps with Cartopy: The US Airline Network where we introduce some of the amazing functionality of Cartopy.
After several months of working behind the scenes, we can finally announce what has been keeping us busy (and away from the usual blogging schedule which we hope to resume soon). We’ve just completed recording and editing two new long form on-demand videos.
1. Natural Language Processing, has almost five and a half hours of new NLP content using NLTK and Keras that will bring you up to speed on state of the art NLP techniques and approaches. And while we’re on the topic of NLP, we would like to remind you that the next NLP webinar, NLP with Deep Learning for Everyone is coming up on November 19. Sign up now so you don’t miss out!
2. Times Series Analysis for Everyone, is six hours of videos covering data pre-processing, visualization, ARIMA, ARCH and Deep Learning models for Time series analysis.
On our regularly scheduled content, we have a deep dive into graph neural networks with Computation graphs and graph computation and Graph Representation Learning: From Simple to Higher-order Structures. We also explore a Visual Git Reference and Cognition Without Computation.
From the halls of academia we have an exploration of how conspiracists exploited COVID-19 science, the effects of remote work on collaboration among information workers and how hierarchical Transformers Are More Efficient Language Models.
Finally, this weeks ‘Data Science Book’ highlight is “Graph Representation Learning” by W. Hamilton. As always you can find all the previous book recommendations on our website. In the video of the week we have an An Introduction to Graph Neural Networks: Models and Applications.
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 enjoy this newsletter, just go ahead and forward this email to them. This will help us spread the word!
The D4S Team
The latest post on the Graphs for Data Science substack: Network Assortativity and the Configurational Model is now out.You should Sign Up to make sure you never miss a post!
The latest post on the Visualization for Data Science substack: Geographical Maps with Cartopy: The US Airline Network is now out. Don’t forget to Subscribe so you’re first in line to receive every post.
The latest post in the CoVID-19 series, ‘How to model the effects of vaccination’ takes a look at how simple modifications of the SIR model can help us better understand how vaccines work. As usual, all the code is available in GitHub: http://github.com/DataForScience/Epidemiology101
The latest post in the Causality series covers section ‘3.7 — Mediation’, a recipe to calculate the controlled directed effect. The code for each blog post in this series is hosted by a dedicated GitHub repository: https://github.com/DataForScience/Causality
This weeks Data Science Book is “Graph Representation Learning” by W. Hamilton. This short (141 pages) book gives a grounded, well-written, and to the point introduction to representation learning for graphs that helps you grasp the fundamental concepts as well understand when to and when not to. The extensive bibliography provides entry points for further study for the motivated reader. The algorithm descriptions are clear and intuitive in a way that will give you a leg up to implement pre-existing algorithm and even develop your own variations.
Tutorials and blog posts that came across our desk this week.
- Computation graphs and graph computation [breandan.net]
- Surprising Limits Discovered in Quest for Optimal Solutions [quantamagazine.org]
- Cognition Without Computation [spectrum.ieee.org]
- Graph Representation Learning: From Simple to Higher-order Structures [opendatascience.com]
- How to flatten a list in Python [treyhunner.com]
- A Visual Git Reference [marklodato.github.io]
- Facebook to Shut Down Use of Facial Recognition Technology [bloomberg.com]
Some of the most interesting academic papers published recently
- How conspiracists exploited COVID-19 science (K. H. Jamieson)
- Cryptic transmission of SARS-CoV-2 and the first COVID-19 wave (J. T. Davis, M. Chinazzi, N. Perra, K. Mu, A. Pastore y Piontti, M. Ajelli, N. E. Dean, C. Gioannini, M. Litvinova, S. Merler, L. Rossi, K. Sun, X. Xiong, I. M. Longini Jr, M. E. Halloran, C. Viboud, A. Vespignani)
- The effects of remote work on collaboration among information workers (L. Yang, D. Holtz, S. Jaffe, S. Suri, S. Sinha, J. Weston, C. Joyce, N. Shah, K. Sherman, B. Hecht, J. Teevan)
- Two provably consistent divide-and-conquer clustering algorithms for large networks (S. S. Mukherjee, P. Sarkar, P. J. Bickel)
- Characterizing partisan political narrative frameworks about COVID-19 on Twitter (E. Jing, Y.-Y. Ahn)
- Hierarchical Transformers Are More Efficient Language Models (P. Nawrot, S. Tworkowski, M. Tyrolski, Ł. Kaiser, Y. Wu, C. Szegedy, H. Michalewski)
- Identification and prioritization of urban traffic bottlenecks (N. Serok, S. Havlin, E. B. Lieberthal)
- Community structure detection algorithm based on link prediction (G. Dai, Q. Wang, B. Xu, L. Sun)
Interesting discussions, ideas or tutorials that came across our desk.
An Introduction to Graph Neural Networks: Models and Applications
All the videos of the week are now available in our Youtube playlist.
Opportunities to learn from us:
- Nov 19, 2021 — NLP with Deep Learning for Everyone [Register]
- Dec 02, 2021 — Applied Probability Theory for Everyone [Register]
- Dec 17, 2021 — Transforming Excel Analysis into Python and pandas Data Models [Register]
- Jan 12, 2021 — Graphs and Network Algorithms for Everyone [Register] 🆕
- Jan 26, 2021 — Why and What If — Causal Analysis for Everyone [Register] 🆕
Thank you for subscribing to our weekly newsletter with a quick overview of the world of Data Science and Machine Learning. Please share with your contacts to help us grow!
Publishes on Sunday.