Issue #244

May 8, 2024

​(view in browser)​

​

Dear Reader,

Welcome to the 244th edition of the Data Science Briefing!

The latest medium post on the Epidemiology series: Epidemiology 303: Metapopulation models, where we explore how to connect multiple populations through a travel matrix is now out. You can catch up on the latest in the Graphs for Data Science substack: k-core Decomposition, or in the Viz4Sci series, The Effects of Vaccination.

In our regularly scheduled content, we Understand Stein's paradox, learn why LLMs Can’t Do Probability, explore A Beginner’s Guide to Vector Embeddings, and how Bitcoin Forensic Analysis Uncovers Money Laundering Clusters and Criminal Proceeds.

On the academic front, we explore The Effect of Vaccine Mandates on Disease Spread, A Primer on the Inner Workings of Transformer-based Language Models, and The Shape of Money Laundering.

This week's book recommendation is "Natural Language Processing with Transformers" by L. Tunstall, L. von Werra, and T. Wolf. You can find all the previous book recommendations on our website. In this week's video, we have a lecture by Leslie Lamport about Thinking Above The Code.

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, go ahead and forward this email to them. This will help us spread the word!

Semper discentes,

The D4S Team

This week's book is "Natural Language Processing with Transformers" by L. Tunstall, L von Werra and T. Wolf. As an avid natural language processing enthusiast (NLP), I recently delved into "Natural Language Processing with Transformers" with great anticipation. Authored by experts in the field, this book not only met but exceeded my expectations, offering a comprehensive exploration of the groundbreaking advancements in NLP powered by transformers.

From the outset, the book strikes an excellent balance between theoretical underpinnings and practical applications. Including code snippets and implementation tips further enhances the learning experience, allowing readers to gain proficiency in applying these powerful techniques to real-world problems.

In conclusion, "Natural Language Processing with Transformers" is a must-read for anyone interested in unlocking the full potential of modern NLP techniques. Whether you're a researcher, a student, or a practitioner seeking to stay ahead of the curve, this book offers a treasure trove of knowledge and practical wisdom. Engaging, informative, and inspiring, it is sure to leave a lasting impact on anyone passionate about the intersection of language and technology.

1. ​Understanding Stein's paradox [joe-antognini.github.io]
2. ​Not all Graphs are Trees​ [buttondown.email]
3. ​LLMs Can’t Do Probability​ [brainsteam.co.uk]
4. ​Bitcoin Forensic Analysis Uncovers Money Laundering Clusters and Criminal Proceeds [thehackernews.com]
5. ​A Beginner’s Guide to Vector Embeddings​ [timescale.com]
6. ​SQL Schema Generation With Large Language Models​ [thenewstack.io]
7. ​What’s Going On in This Graph? [nytimes.com]

• ​The Effect of Vaccine Mandates on Disease Spread (R. K. Acton, W. Cao, E. E. Cook, S. A. Imberman, M. F. Lovenheim)
• ​Scaling hierarchical agglomerative clustering to trillion-edge graphs​ (L. Dhulipala, J. Łącki)
• ​A Primer on the Inner Workings of Transformer-based Language Models​ (J. Ferrando, G. Sarti, A. Bisazza, M. R. Costa-jussà)
• ​KAN: Kolmogorov-Arnold Networks​ (Z. Liu, Y. Wang, S. Vaidya, F. Ruehle, J. Halverson, M. Soljačić, T. Y. Hou, M. Tegmark)
• ​Network reconstruction via the minimum description length principle​ (T. P. Peixoto)
• ​The Matrix: A Bayesian learning model for LLMs​ (S. Dalal, V. Misra)
• ​The Shape of Money Laundering: Subgraph Representation Learning on the Blockchain with the Elliptic2 Dataset​ (C. Bellei, M. Xu, R. Phillips, T. Robinson, M. Weber, T. Kaler, C. E. Leiserson, Arvind, J. Chen)

Leslie Lamport: Thinking Above the Code

​

All the videos of the week are now available in our Youtube playlist.