./episode_129.sh

📚 "If people knew how hard I worked to get my mastery, it wouldn't seem so wonderful at all.” – Michelangelo

May 21, 2023

Hey friends & nerds! 👋

Welcome to the Sunday Science Newsletter where we explore science, systems & tools that help us become smarter scientists.

Work with me 🤝

🤓 Lukasz Skotny | Expert Interview #3

Discover the world of science through our interview with Lukasz Skotny. Explore his groundbreaking research and gain valuable insights into the scientific process. Don't miss this opportunity to learn from one of the brightest minds in the field of FEA!

Read the Interview

🚀 Langley Unitary Plan Wind Tunnel

💻 Physics-Constrained ML for Scientific Computing

A fundamental challenge is that the predictions of deep-learning models trained on physical data typically ignore fundamental physical principles. Such models might, for instance, violate system conservation laws: the solution to a heat transfer problem may fail to conserve energy, or the solution to a fluid flow problem may fail to conserve mass.

Similarly, a model’s solution may violate boundary conditions — say, allowing heat flow through an insulator at the boundary of a physical system. This can happen even when the model’s training data includes no such violations: at inference time, the model may simply extrapolate from patterns in the training data in an illicit way.

Paper - Learning Physical Models

🌀 Advanced Fluid Mechanics 2: The Navier-Stokes Equations for Viscous Flows

Learn to apply the Navier-Stokes equations to viscous-dominated flows; including pipe flows, channel flows and free surface flows, use dynamical similarity and dimensional analysis, Stokes flows, similarity solutions and transient responses, lubrication analysis and surface tension.

Learn on edX

🎓 Introducing LLM University - The Go-To Learning Resource for NLP

My good old friend Luis Serrano will teach you on LLMs. Not sponsored - just think an amazing opportunity to learn more about this great technology!

NLP University has five main modules, and two appendices.

Ways to learn

The material they’ve put together can be used in two ways:

Sequential: If you want to start from the very beginning, the course will take you through the basics of Large Language Models and their architecture, and then a lot of practice, including coding, and prompt engineering. The course starts with Large Language Models and requires very little background knowledge. However, if you'd like to brush up on the basics of Machine Learning and Natural Language Processing, this material is in Appendix 1.
Non-Sequential: If you feel like you already know the basics of NLP and LLMs, or you have a particular project in mind, you can skip ahead to the later modules. If you have a specific goal in mind, you are more than welcome to go directly to that particular module.

Learn More

📚Rules to get ahead of 99% of people.

Some controversial points for sure. Let me know what you think and reach out!

Full Blog

💻 Engineering Tool of the Week – FEniCSx

FEniCSx is a popular open-source computing platform for solving partial differential equations (PDEs). FEniCSx enables users to quickly translate scientific models into efficient finite element code. With the high-level Python and C++ interfaces to FEniCSx, it is easy to get started, but FEniCSx offers also powerful capabilities for more experienced programmers. FEniCSx runs on a multitude of platforms ranging from laptops to high-performance clusters.

Offical Website.

📚 Book of the Week

The Model Thinker: What You Need to Know to Make Data Work for You

Work with data like a pro using this guide that breaks down how to organize, apply, and most importantly, understand what you are analyzing in order to become a true data ninja.

From the stock market to genomics laboratories, census figures to marketing email blasts, we are awash with data. But as anyone who has ever opened up a spreadsheet packed with seemingly infinite lines of data knows, numbers aren't enough: we need to know how to make those numbers talk.

Get on Amazon.