Expand description
Machine learning, and dynamic automatic differentiation implementation.
Modules§
- activation
- Activation functions are differentiable non-linearities applied to the output of layers.
- array
- An n-dimensional array, with automatic differentation.
- cost
- Cost functions compute the loss given a target, and are used for the backward pass.
- initializer
- Initializers initialize the parameters of a model.
- layer
- Implementations of neural network layers.
- model
- A supervised neural network model, which computes a forward pass, and updates parameters based on a target.
- numbers
- Floating point type wrapper, which may be changed to
f32when the feature “f32” is active. - optimizer
- Implementations of gradient descent optimizers, to optimize the parameters of a model.
Macros§
- arr
- Creates an
Array, which is row-major, with either: