SciML/SciMLBook

Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)

What it solves

This project provides a comprehensive, up-to-date educational resource for understanding the intersection of high-performance parallel computing and scientific machine learning (SciML).

How it works

It serves as a live, evolving textbook based on lecture notes from the MIT course 18.337J/6.338J. The content is maintained as a website built with Franklin.jl, utilizing Julia Markdown documents that are processed to generate the final educational pages.

Who it’s for

Students, researchers, and developers interested in learning how to apply machine learning techniques to scientific problems while leveraging parallel computing for high-performance execution.

Highlights

  • A living document that is continuously updated with the latest methods in SciML.
  • Covers advanced techniques for high-performance computing.
  • Based on established MIT curriculum material.
  • Accessible online as a structured, easy-to-read book.

Related

  • Project
    pykeen/pykeen

    PyKEEN is a Python library for training and evaluating knowledge‑graph embedding models, offering dozens of models, many benchmark datasets, and a high‑level pipeline API.

  • Project
    tensorflow/recommenders

    A TensorFlow-based library for building recommender system models, supporting the full workflow from data preparation to deployment.

  • Project
    chenglou/handwired

    Handwired converts regular JavaScript code into a differentiable program made only of matrix multiplication and ReLU, enabling GPU‑accelerated execution and gradient‑based experiments without any training.

  • Project
    deepmodeling/deepmd-kit

    A deep learning package that turns quantum-mechanical reference data into fast, scalable interatomic potentials for molecular and materials science simulations.