Expand description
§Concision
Concision aims to be a complete machine learning library written in pure Rust.
Modules§
- Data
- Functional
- Graph Neural Networks (GNN)
- Initialization
- Kolmogorov-Arnold Networks (KAN)
- Linear Models
- Mathematics
- Operations
- Transformers
Macros§
- AS
Structs§
Enums§
Constants§
- The default model size for any given model
- The default epsilon value for floating point operations
Traits§
- A trait for applying a function to a type
- Backward describes an object capable of backward propagation.
- A trait used to denote objects that may be used for configuring various items
- Configuration describes composite configuration objects; A configuration object is allowed to inherit from another configuration object
- Decrement generally describes an object capable of decrementing itself;
- Forward describes an object capable of forward propagation.
- ForwardIter describes any iterators whose elements implement Forward. This trait is typically used in deep neural networks who need to forward propagate across a number of layers.
- This trait provides the base methods required for initializing an ndarray with random values. Initialize is similar to RandomExt, however, it focuses on flexibility while implementing additional features geared towards machine-learning models; such as lecun_normal initialization.
- This trait extends the Initialize trait with methods for generating random arrays from various distributions.
- This trait is used to fill an array with a value based on a mask. The mask is a boolean array of the same shape as the array.
- A
Module
defines any object that may be used as a layer in a neural network. Config is a type that defines the configuration of the module; including any and all hyperparameters. Params is a type that defines the parameters of the module; typically references a Linear set of parameters { weights, bias } - A trait for sequential data structures; This trait is implemented for iterators that have a known length.
Functions§
- Creates an n-dimensional array from an iterator of n dimensional arrays.
- creates a matrix from the given shape filled with numerical elements [0, n) spaced evenly by 1
- Round the given value to the given number of decimal places.
- Creates a larger array from an iterator of smaller arrays.
- Returns the lower triangular portion of a matrix.
- Returns the upper triangular portion of a matrix.