mattjj / autodidact
A pedagogical implementation of Autograd
☆978Updated 4 years ago
Alternatives and similar repositories for autodidact:
Users that are interested in autodidact are comparing it to the libraries listed below
- Hardware accelerated, batchable and differentiable optimizers in JAX.☆962Updated 3 weeks ago
- functorch is JAX-like composable function transforms for PyTorch.☆1,424Updated this week
- Optax is a gradient processing and optimization library for JAX.☆1,875Updated this week
- JAX - A curated list of resources https://github.com/google/jax☆1,796Updated 2 months ago
- JAX-based neural network library☆3,021Updated this week
- Fast and Easy Infinite Neural Networks in Python☆2,335Updated last year
- ⚡️Optimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.☆901Updated last month
- ☆848Updated this week
- Constrained optimization toolkit for PyTorch☆678Updated 3 years ago
- KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows☆1,091Updated last week
- A Graph Neural Network Library in Jax☆1,427Updated last year
- Fast Block Sparse Matrices for Pytorch☆545Updated 4 years ago
- Extending JAX with custom C++ and CUDA code☆394Updated 8 months ago
- Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/☆2,336Updated last week
- Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.☆1,429Updated this week
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆580Updated 4 months ago
- A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods☆1,473Updated last year
- Normalizing flows in PyTorch. Current intended use is education not production.☆861Updated 5 years ago
- Tutorial for building a custom CUDA function for Pytorch☆511Updated 6 years ago
- A PyTorch implementation of L-BFGS.☆600Updated 2 years ago
- Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/☆1,390Updated this week
- ☆430Updated 6 months ago
- code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".☆639Updated 4 years ago
- Efficiently computes derivatives of NumPy code.☆7,254Updated this week
- Differentiable SDE solvers with GPU support and efficient sensitivity analysis.☆1,638Updated 4 months ago
- ☆1,311Updated 3 weeks ago
- Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/☆1,611Updated last week
- Course notes☆684Updated last year
- Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes…☆241Updated 4 years ago
- ☆797Updated 3 weeks ago