Towards Data Science

Help us build a better TDS! 🚀 We're conducting our first annual reader survey to learn more about you, your role, and what you want to read. Your feedback will directly shape our content and platform. Take our quick 5-minute survey 👉 https://lnkd.in/gZyKVr6H

The Roofline Model offers a powerful visual analysis of application performance optimization. Dive into Rachit Jain's full article to learn how to bridge the gap between theoretical and real-world application performance with roofline modeling.

In this Author Spotlight, Claudia Ng breaks down her biggest lesson in ML: domain expertise matters more than algorithmic complexity. She shares insights on mentoring, career transitions, and the realities of working with AI.

Can you really use two date tables in a single Power BI report? Salvatore Cagliari explains this data modeling technique, detailing how a second date table enables waterfall charts to track growth from a specific starting value, even when using drill-throughs.

The rapid evolution of LLMs is transforming industries and offers great potential to benefit healthcare. Evaluation-driven development is essential for building reliable, impactful AI solutions in healthcare and elsewhere. Read Robert Martin-Short's full article now.

Is this the future of Python numerical computation? Tom Reid introduces cuNumeric, an NVIDIA library designed as a high-performance, drop-in replacement for NumPy.

That LLM app is not performing, but you don’t have enough labeled data to fine-tune it. Aparna Dhinakaran introduces Prompt Learning, an optimization approach that uses English feedback to make powerful changes to your LLM’s prompt with just a few examples.

Tom Reid breaks down Google’s LangExtract tool, a powerful new NLP and data extraction library that rethinks how we approach RAG. He explains the features, use cases, and why it stands out in Google’s AI streak.

That LLM app has a ton of potential, but how do you turn it into a product? This article by Prasann Pradeep Patil is your step-by-step guide to powering an application with LLMs, from defining the use case to evaluating and deploying your model.

Gustavo R Santos breaks down an AI built with LangGraph and SciPy that reads documentation to guide decision-making. He explains how it helps data scientists stop guessing and start applying the right statistical methods with confidence.