—
Feeling inspired to write your first TDS post? We’re always open to contributions from new authors.
When we encounter a new question, topic, or challenge, taking the first step forward is often the most difficult part. That’s the moment where self-doubt kicks in, our existing knowledge feels hazy and inadequate, and procrastination often appears like the only acceptable choice.
Our standout articles this week won’t magically solve every single challenge you’ll ever face as a data scientist or machine learning engineer, but what they do all offer is a pragmatic, action-focused roadmap for overcoming those initial hurdles in the learning process.
From expanding your foundational statistics knowledge to becoming a better writer, these articles cover a wide range of skills and domains that successful data professionals excel at. Enjoy your reading!
- What Is Causal Inference?
From randomized controlled trials and difference-in-differences to synthetic control and A/B testing, Khin Yadanar Lin presents an accessible, detailed (but not overwhelming) introduction to the ever-crucial topic of causal inference and its practical applications in common daily workflows. - Understanding Conditional Probability and Bayes’ Theorem
Sometimes it helps to trace a concept all the way back to its inception to gain a full understanding of its importance—and use cases. Sachin Date offers precisely that kind of patient retrospective in his excellent primer on the origins of conditional probability and Bayes’ theorem and how they play out in the context of regression analysis. - Deep Dive into LSTMs and xLSTMs by Hand
Combining a strong narrative flow and well-crafted illustrations has been a winning approach in Srijanie Dey, PhD’s “By Hand” series; her latest installment is no exception, diving deep into the underlying math of long short-term memory networks (LSTMs) and their more recent variant, xLSTMs (or extended long short-term memory networks).
- Linear Programming Optimization: Foundations
For the inaugural post in his series on linear programming, “a powerful optimization technique that is used to improve decision making in many domains,” Jarom Hulet focuses on establishing a strong foundation for learners, covering the key concepts you need to be aware of before you move on to more complex, hands-on approaches. - How To Start Technical Writing & Blogging
We all know how to write, of course, but taking the leap towards a more intentional and consistent writing practice can be daunting. Egor Howell has been a successful blogger on data science (and other technical topics) for years, and he now shares actionable insights to help others grow in this potentially career-boosting area.
Ready to take your learning in other directions? Don’t miss our other recommended reads this week, which cover cutting-edge topics in AI, data visualization, and more.
- Engaging and thought-provoking, Joshua Banks Mailman, Ph.D.’s deep dive on counterfactuals invites us to examine how they might “help us think differently about the pitfalls and potentials of Generative AI.”
- If you’d like to catch up on new research around graph-structured data, we strongly recommend Qitian Wu’s comprehensive overview of three recent papers in this exciting machine learning subfield.
- How have recent updates to ChatGPT affected its performance in data-analysis tasks? Yu Dong reflects on the chatbot’s potential as a future business-intelligence tool.
- Building on his past success in developing innovative data-visualization formats, Nick Gerend unveils his latest creation: path-swarm and super-swarm charts, using circle arrangements to represent individual observations.
- For anyone looking to jump right into some code, Shreya Rao is here to help with a quick and concise guide to implementing neural networks in TensorFlow and PyTorch.
- Why do data-quality projects rarely deliver on their potential? Barr Moses unpacks the challenges of structuring them effectively, and shares actionable insights on how to avoid past mistakes.
- We end our weekly selection with another fun—and useful—hands-on tutorial: Carmen Adriana Martínez Barbosa, PhD. and José Arturo Celis-Gil’s walkthrough of a cloud-detection and segmentation project, which leverages satellite images and several powerful algorithms.
Thank you for supporting the work of our authors! 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, don’t hesitate to share it with us.
Until the next Variable,
TDS Team