You will never miss a new edition of variablea weekly newsletter featuring top-notch selections including editor picks, deep diving, and community news.
It concludes another eventful month. The month has published dozens of new articles on cutting edge and evergreen topics. From Mathfor Machine Learning Engineers to the inner workings of the Model Context Protocol.
Read in May to explore our most arduous stories. Our community has found the most useful, practical and thought-inspired articles.
If you're inspired to write about your passion project or recent discoveries, don't hesitate to share your work with us. We have always been open for submissions from new authors, and our author payment programme has been streamlined considerably this month.
How to learn the mathematics needed for machine learning
Everyone loves a good roadmap. Suitable Case: Egor Howell's Practical Guide for ML Practitioners. It provides an overview of the best approaches and resources for acquiring the baseline knowledge required for linear algebra, statistics, and calculations.
Are you new to LLMS? Start here
I am pleased to be publishing another great guide this month. Everything about Alessandra Costa's beginner intro, lag, tweaks, agents and more.
Inheritance: Software Engineering Concept Data Scientists Need to Know to Succeed
Still on the subject of core skills, Benjamin Lee shared an in-depth introductory book on inheritance, an essential concept of coding.
Other highlights
Find out more about last month's most popular and widely distributed articles, spanning a variety of topics such as data engineering, healthcare data, and time series forecasting.
- Sandi Besen introduced the Agent Communication Protocol, an innovative framework that allows AI agents to collaborate “between teams, frameworks, technologies, and organizations.”
- Staying on the constant topic of Agent AI, Hailee Kuach compiled it very A useful resource for those who want to learn more about MCP (Model Context Protocol).
- How can I implement multiple linear regression analyses on actual data? Junior Junbong explains the process in a patient tutorial.
- Learn how machine learning libraries accelerate non-ML computations. ThomasReid unleashes some of Pytorch's little-known (but very powerful) use cases.
- In one of the best of last month, Yagmur Gulec walked us around preventive health projects that leverage a machine learning approach.
- From simple averages to blending strategies, the latest in Nikhil Dasari's series focuses on how you can customize the model baseline for time series predictions.
Meet our new authors
We are excited to welcome a fresh cohort of data science, machine learning and AI experts each month. Don't miss some of our latest contributors' work:
- Iwai is a machine learning engineer and founder and CEO of the Agent-AI Space.
- Mehdi Yazdani, an AI researcher in Florida, shares the latest work on training neural networks for two purposes.
- Joshua Nishinth A is involved in the TDS community with extensive experience in data science, deep learning and engineering.
I love publishing articles from new authors, so if you recently wrote an interesting project walkthrough, tutorial, or theoretical reflection on any of our core topics, why not share it with us?
