|
Welcome to the Sep 18th edition of the Data Science Briefing!
We want to remind you that the very first edition of the LLMs for Data Science webinar will be held Tomorrow! There are still a couple of spots left, so Register now!
The most recent post on the Epidemiology series, Epidemiology 303: Metapopulation Models, explores how to connect multiple populations through a travel matrix. In the graph subsection, you'll find all you need to know about k-core Decomposition, while in the Visualization section, you can explore The Effects of Vaccination through a WSJ visualization.
In our regularly scheduled content, we learn how cosine similarity works, How LLMs Got Lost in the Network and Discovered Graph Reasoning and explore B-trees and database indexes.
On the academic front, we ground AI in reality with a little help from Data Commons, review the structure of street networks, and learn to Live with the fact that LLMs Will Always Hallucinate.
This week's book recommendation is "Why Machines Learn: The Elegant Math Behind Modern AI" by A. Ananthaswamy. You can find all the previous book recommendations on our website. In this week's video, we have a lecture by Terence Tao on AI and Mathematics.
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 "Why Machines Learn: The Elegant Math Behind Modern AI" by A. Ananthaswamy. The book introduces the main ideas and developments of Artificial Intelligence clearly and concisely. Starting with the invention of the Perceptron in the 50s, through all the significant developments of the last several decades, such as Support Vector Machines, Hopfield Networks, and Backpropagation, to the latest developments in Large Language Models. Ananthaswamy explains how they fit in the historical development of Computer Science and AI, as well as how they connect to insights originating in biology and psychology.
The book targets a general audience familiar with basic math. Mathematical concepts such as probability and linear algebra are introduced in an intuitive way that provides just enough detail to understand the more technical parts of the text. Overall, a great resource whether your reviewing these concepts or encountering them for the first time.
- How does cosine similarity work? [tomhazledine.com]
-
B-trees and database indexes [planetscale.com]
-
Learning to Reason with LLMs [openai.com]
- Geometric Search Trees [g-trees.github.io]
-
Novel Architecture Makes Neural Networks More Understandable [quantamagazine.org]
-
How I Mastered Data Structures and Algorithms [medium.com/algomaster-io]
-
How the LLM Got Lost in the Network and Discovered Graph Reasoning [towardsdatascience.com]
- Grounding AI in reality with a little help from Data Commons (J. Chen, P. Ramaswami)
-
Collaborative forecasting of influenza-like illness in Italy: the Influcast experience (S. Fiandrino, A. Bizzotto, G. Guzzetta, S. Merler, F. Baldo, E. Valdano, A. M. Urdiales, A. Bella, F. Celino, L. Zino, A. Rizzo, Y. Li, N. Perra, C. Gioannini, P. Milano, D. Paolotti, M. Quaggiotto, L. Rossi, I. Vismara, A. Vespignani, N. Gozzi)
-
Self-similarity of temporal interaction networks arises from hyperbolic geometry with time-varying curvature (S. Dutta, D. Das, T. Chakraborty)
-
A review of the structure of street networks (M. Barthelemy, G. Boeing)
-
A Review of Graph Neural Networks in Epidemic Modeling (Z. Liu, G. Wan, B. A. Prakash, M. S. Y. Lau, W. Jin)
-
LLMs Will Always Hallucinate, and We Need to Live With This (S. Banerjee, A. Agarwal, S. Singla)
-
Bayesian clustering with uncertain data (K. Nicholls, P. D. W. Kirk, C. Wallace)
Terence Tao at IMO 2024: AI and Mathematics
 All the videos of the week are now available in our Youtube playlist.
Upcoming Events:
Opportunities to learn from us
On-Demand Videos:
Long-form tutorials
|
|
|
|
