Expand description
This crate is a Rust-native tensor and math library, developed for Project Elara. It aims to be a basic implementation of common machine learing and scientific computing tools in Rust. It tries to give a Rust experience similar to SciPy, NumPy, and PyTorch/TensorFlow, offering:
- Tensors: N-dimensional differentiable arrays (via
Tensor) - An implementation of reverse-mode automatic differentiation
- Numerical solvers for calculus (only numerical integration/quadrature is fully-supported at the moment, the ODE solver has been moved to
elara-array)
To get started, just run cargo install elara-math to add to your project. We offer several examples in our GitHub repository to reference and learn from.
Modules§
- prelude
elara-mathprelude
Macros§
- count
- A macro for counting the number of args passed to it
- scalar
- Macro for quickly creating scalar tensors
- tensor
- Macro for quickly creating tensors
Structs§
- Linear
- A 2D linearly densely-connected layer
- Model
- A neural network model with a keras-inspired API
- Tensor
- A PyTorch-like differentiable tensor type
- Tensor
Data - Backing data for
Tensor
Enums§
- Activations
- Common activation functions
- Optimizers
- Common optimizers
Traits§
- Layer
- A general trait of a layer of a neural network
Functions§
- mse
- Mean squared error function