Issue #241

Apr 17, 2024

​(view in browser)​

​

Dear Reader,

Welcome to the 241st 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.

This week, we're proud to announce the latest webinar series on Generative AI: LangChain for Generative AI Pipelines has just been announced for June 5th, and the Registrations are already open. Don't miss out!

In our regularly scheduled content, we learn how Your (Graph) Data Fits in Memory, how to Reimplement Redis with SQLite, and how to Simulate Ecosystems.

On the academic front, we dive into the scaling law of real traffic jams under varying travel demand, who and what gets recognized in peer recognition, and whether or not the Atlantic Overturning Circulation Approaching a Tipping Point.

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 tutorial on Attention in transformers, visually explained.

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. ​Your (Graph) Data Fits in Memory [jazco.dev]
2. ​Mathematician Who Shed Light on Randomness in Algorithms Wins Top Prize in Computing​ [smithsonianmag.com]
3. ​Reimplement Redis with SQLite [github.com/nalgeon]
4. ​Shape typing in Python​ [jameshfisher.com]
5. ​Good News Against Dengue​ [science.org]
6. ​Simulating Ecosystems​ [cantorsparadise.com]
7. ​Explained: Tokens and Embeddings in LLMs​ [medium.com]

• ​Higher-order Granger reservoir computing: simultaneously achieving scalable complex structures inference and accurate dynamics prediction (X. Li, Q. Zhu, C. Zhao, X. Duan, B. Zhao, X. Zhang, H. Ma, J. Sun, W. Lin)
• ​Reconstructing the evolution history of networked complex systems​ (J. Wang, Y.-J. Zhang, C. Xu, J. Li, J. Sun, J. Xie, L. Feng, T. Zhou, Y. Hu)
• ​Scaling law of real traffic jams under varying travel demand​ (R. Chen, Y. Lin, H. Yan, J. Liu, Y. Liu, Y. Li)
• ​Is the Atlantic Overturning Circulation Approaching a Tipping Point?​ (S. Rahmstorf)
• ​Who and what gets recognized in peer recognition​ (M. Sundstrom, L. N. Simpfendoerfer, A. Tan, A. B. Heim, N. G. Holmes)
• ​Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length​ (X. Ma, X. Yang, W. Xiong, B. Chen, L. Yu, H. Zhang, J. May, L. Zettlemoyer, O. Levy, C. Zhou)
• ​Dynamical stability and chaos in artificial neural network trajectories along training​ (K. Danovski, M. C. Soriano, L. Lacasa)

Attention in transformers, visually explained

​

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