# SciML/SciMLBook

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

Repository: https://github.com/SciML/SciMLBook
Canonical: https://ross.abutalabs.com/products/scimlbook
Homepage: https://book.sciml.ai/
Language: HTML
License Family: other
Topics: differential-equations, scientific-machine-learning, neural-networks, numerical-methods, gpu-computing, stiff-equations, lecture-notes, performance-engineering, parallelism, scientific-simulators, neural-ode, neural-sde, sciml
Last push: 2026-08-26T04:56:32+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 8, longevity 100
- inputs: {"age_days": 2561, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2036, forks 375 (observed 2026-08-28T04:06:08.078984+00:00)

## What it is
An open online book compiling lecture notes from MIT course 18.337J/6.338J on parallel computing and scientific machine learning (SciML). It is a continuously updated Franklin.jl website covering differential equations, neural ODEs/SDEs, automatic differentiation, GPUs, and high-performance scientific computing.

## Use cases
- learn scientific machine learning from scratch
- study neural ODEs and neural SDEs
- learn parallel computing and GPU programming for scientific computing
- understand how to solve stiff differential equations numerically
- find course materials on physics-informed machine learning
- learn automatic differentiation for differential equation solvers
- study performance engineering and profiling for scientific simulations

## When to choose
- you want a free, in-depth textbook-style introduction to SciML and parallel computing
- you are teaching or self-studying differential equation solving combined with machine learning
- you want continuously updated lecture notes from an active research group

## When to avoid
- you need runnable software or a library rather than reading material
- you want a language-agnostic or Python-only tutorial (examples are Julia-centric)
- you need a formal certification or instructor-led course rather than self-paced notes

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, gpu-computing, simulation, documentation, math
- domain: tutorials, machine-learning, gpu-computing
- platform: jvm-scripting
- tags: lecture-notes, differential-equations, neural-ode, parallel-computing, julia, scientific-computing, high-performance-computing, mit-course, scientific-machine-learning, algorithms, web-server

## Member repositories
- SciML/SciMLBook (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:08.078984+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:59:18.794863+00:00, confidence not recorded.
  - readme: https://github.com/SciML/SciMLBook (fetched 2026-08-28T04:06:08.078984+00:00, sha e7b048ffe289)
  - homepage: https://book.sciml.ai/ (fetched 2026-08-29T10:38:48.572771+00:00, sha 16a8cec92d79)
- Data as of 2026-08-30T08:39:29.467469+00:00.