[go: up one dir, main page]
Skip to content
View patrick-kidger's full-sized avatar
2.2k followers · 2 following

Sponsors

@Artur-Galstyan
@dlwh

Achievements

Achievement: Pair Extraordinairex2Achievement: Galaxy Brainx2Achievement: QuickdrawAchievement: YOLOAchievement: Starstruckx3Achievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex2Achievement: Galaxy Brainx2Achievement: QuickdrawAchievement: YOLOAchievement: Starstruckx3Achievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Block or report patrick-kidger

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
patrick-kidger/README.md

JAX scientific ML ecosystem:

Probably the reason you're here. I would highlight:

  1. Equinox: elegant neural networks. GitHub Repo stars

  2. Diffrax: numerical ODE/SDE solvers. GitHub Repo stars

  3. jaxtyping: shape/dtype annotations for arrays. GitHub Repo stars

  4. Lineax: linear/least-squares solvers. GitHub Repo stars

  5. Optimistix: root finding, least squares, etc. GitHub Repo stars

Other links:

Me:

I currently wear multiple hats across bio/ML/CS at Cradle.bio. These days I am generally interested in scientific ML, and specifically the application of ML to unsolved problems in biology!

I also hold an honorary lectureship at Imperial College London. In past lives I previously wore the same multitude of hats at Google X, and did my PhD at the University of Oxford.

Pinned Loading

  1. google-research/torchsde google-research/torchsde Public

    Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

    Python 1.6k 200

  2. torchtyping torchtyping Public

    Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

    Python 1.4k 34

  3. equinox equinox Public

    Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

    Python 2.1k 142

  4. diffrax diffrax Public

    Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

    Python 1.4k 130

  5. jaxtyping jaxtyping Public

    Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

    Python 1.2k 62

  6. NeuralCDE NeuralCDE Public

    Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)

    Python 627 69