TDS Newsletter: November must – Read on GraphRag, ML projects, LLM-Powered Time-Seime-Series analysis, and more
Never miss a new edition of the DiversityOur weekly magazine that includes a top notch selection of editors' picks, in-depth awards, community news, and more.
The end of the year is just a few weeks away, and our writers and readers aren't showing any signs of slowing down.
We are very pleased to have published some of our strongest content of the year last month: Practical Guidelines for LLM careers, skills development, and in-depth tools, and a deep dive into newly introduced tools, among other newly introduced topics, among other stomaut topics. Read on to catch (or recycle) November's most read stories.
Graph rag vs sql rag
Which parabase paramagm yields accurate and insightful results? Reinhard Selelliir puts a look at the performance of two types of rag programs with grafrag and sql rag against each other, using the same data and queries.
Timeline Analysis of LLM Development
In the second part of Sara Nobrega's popular series, we learn about the incentives we need to develop a model (think Arima and LSTM).
How to build machine learning projects that help you get hired
Not all ML portfolios are created equal. EGOR Howell shares time-tested insight into what works – and what doesn't.
Another highlight in November
Don't miss some of the top readings from last month, dealing with nunkpy, multimodal rag, in marimo books, and many other topics – many evergreens – evergreens.
Nupy for absolute beginners: a project-based approach to data analysis, by Ibrahim Salami
Understanding convolutional neural networks (CNN) with Excel, by Angela Shi
Run python up to 150× faster in C, by Thomas Reid
How to Build a Highly Engineered Recovery Program, by IDA SilfverSkiöld
Creating a multimodal rag that responds with text, images and tables from sources, by Partha Sarkar
Why I made the switch to Marimo Notebooks, by Pandey Pandey
Your next 'language model' may not be a big deal after all, by Moulik Gupta
In case you missed it: Our latest author Q & AS
We love sharing our writers' expertise, career insights, and insights into the latest developments in the world of data science and AI. Here are our latest author spots.
- “Plans thinking helps me put the big picture front and center”
Shuai Guo on deep research agents, Analytical Ai vs llm-based agents, and systems thinking.
- “The success of an AI product depends on how real users can interact with its capabilities”
Janna Liperkova on AI strategy, AI products, and how domain knowledge can change the entire design of an AI solution.
Meet our new writers
We hope you take the time to check out the excellent work from TDS Antwerp's latest cohort:
- Jure Leskovec, Stanford professor of Science and Computer Science and entrepreneur, explains why LLMs are not a one-size-fits-all solution for companies.
- Sherin Sunny, a senior engineer at Walmart, walked us through the design of a computer vision project aimed at finding leaves.
- Manuel Franco de La Geña brought us SHATS, a novel shaly-based chaeval method specifically designed for time period models, with which they were created.
We love publishing articles from new writers, so if you've recently written an interesting project walkthrough, tutorial, or theoretical reflection on any of our main topics, why not share it with us?
We'd love your feedback, writers!
Are you an existing TDS writer? We invite you to complete a 5-minute survey to improve the publishing process for all contributors.
