burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
- 16k
- Rust
- Apache-2.0
- 2 d ago
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.
The fastest automatic differentiation library for C++, with Python bindings. Forward, adjoint and higher-order derivatives, checkpointing, Eigen support and JIT. Reproducible benchmarks against CppAD, Adept and autodiff.
Betty: an automatic differentiation library for generalized meta-learning and multilevel optimization
High-Performance LISP-like language for Scientific Computing and AI written in C++
Scientific computing that fits on a microcontroller. Estimation, control, kinematics, Lie groups, calculus, autodiff and linear algebra in stable no_std Rust with no heap, no panics and no unsafe. Run the same code on your laptop and your Cortex-M0.
FastAD is a C++ implementation of automatic differentiation both forward and reverse mode.
Geometry processing utilities compatible with jax for autodifferentiation.
Fazang is a Fortran library for reverse-mode automatic differentiation, inspired by Stan/Math library.
DISCO-DJ: DIfferentiable Simulations for COsmology - Done with Jax
Pure Go machine learning framework. Train, run, and serve ML models with go build. Zero CGo.
A toy deep learning framework implemented in pure Numpy from scratch. Aka homemade PyTorch lol.
Differentiable reparameterization of matrices with orthogonal columns.
A simple library for building computational graphs with autodiff support.