Smyl - A Machine Learning Library in Rust
Smyl is a machine learning library written in Rust, providing a set of tools and abstractions for building and training neural networks.
Features
- Matrix Operations: Smyl provides a
Matrixstruct for efficient matrix operations, including addition, subtraction, multiplication, and more. See the [matrix] module for details. - Activation Functions: Smyl includes common activation functions such as
ReLU and Sigmoid. These are defined in the [
activation] module. - Layers: Smyl defines two main layer types:
SignalLayerandSynapseLayer, which can be used to build neural network architectures. See the [layer] module. - Macros (optional): With the
macrosfeature enabled, Smyl provides a set of macros to simplify the creation of neural networks. These are defined in the [macros] module. - Idx3 Support (optional): With the
idx3feature enabled, Smyl can read and process data in the IDX3 format, commonly used for storing images. This is provided in the [idx3] module.
Getting Started
To use Smyl, add the following to your Cargo.toml file:
[]
= "0.1.0"
Then, in your Rust code, you can import the necessary modules from the prelude:
use *;
Documentation
For more detailed documentation, please refer to the individual module documentation:
- [
matrix]: Matrix operations - [
activation]: Activation functions - [
layer]: Neural network layers - [
macros]: Macros for simplifying neural network creation - [
idx3]: IDX3 data format support
Examples
You can find example usage of Smyl in the [examples] directory of the repository.