May Must-Reads: Math for Machine Learning Engineers, LLMs, Agent Protocols, and More | Towards Data Science

Never miss a new edition of The Variable, our weekly newsletter featuring a top-notch selection of editors’ picks, deep dives, community news, and more.

We’re wrapping up another eventful month, one in which we published dozens of new articles on cutting-edge and evergreen topics alike: from math for machine learning engineers to the inner workings of the Model Context Protocol.

Read on to explore our most-read stories in May—the articles our community found the most useful, actionable, and thought-provoking.

In case you feel inspired to write about your own passion projects or recent discoveries, don’t hesitate to share your work with us: we’re always open for submissions from new authors, and our Author Payment Program just became considerably more streamlined this month.

How to Learn the Math Needed for Machine Learning

Everybody loves a good roadmap. Case in point: Egor Howell‘s actionable guide for ML practitioners, outlining the best approaches and resources for mastering the baseline knowledge they need in linear algebra, statistics, and calculus.

New to LLMs? Start Here

We were delighted to publish another excellent guide this month: Alessandra Costa‘s beginner-friendly intro to all things RAG, fine-tuning, agents, and more.

Inheritance: A Software Engineering Concept Data Scientists Must Know To Succeed

Still on the theme of core skills, Benjamin Lee shared a thorough primer on inheritance, an essential coding concept.

Other May Highlights

Explore more of our most popular and widely circulated articles of the past month, spanning diverse topics like data engineering, healthcare data, and time series forecasting:

• Sandi Besen introduced us to the Agent Communication Protocol, an innovative framework that enables AI agents to collaborate “across teams, frameworks, technologies, and organizations.”

• Staying on the ever-trending topic of agentic AI, Hailey Quach put together a very handy resource for anyone who’d like to learn more about MCP (Model Context Protocol).

• How should you go about implementing multiple linear regression analysis on real-world data? Junior Jumbong walks us through the process in a patient tutorial.

• Learn how a machine learning library can accelerate non-ML computations: Thomas Reid unpacks some of PyTorch’s less-known (but very powerful) use cases.

• In one of last month’s best deep dives, Yagmur Gulec walked us through a preventive-healthcare project that leverages machine learning approaches.

• From simple averages to blended strategies, the latest installment in Nikhil Dasari‘s series focuses on the ways you can customize model baselines for time series forecasting.

Meet Our New Authors

Every month, we’re thrilled to welcome a fresh cohort of Data Science, machine learning, and AI experts. Don’t miss the work of some of our newest contributors:

• Kuriko Iwai is a Machine Learning engineer—and a founder and CEO in the agentic-AI space.

• Mehdi Yazdani, an AI researcher in Florida, shares his latest work on training neural networks with two objectives.

• Joshua Nishanth A joins the TDS community with a wealth of experience in data science, deep learning, and engineering.

We love publishing articles from new authors, so if you’ve recently written an interesting project walkthrough, tutorial, or theoretical reflection on any of our core topics, why not share it with us?

Subscribe to Our Newsletter