Expand description
This module implments various layers for a neural network
Modules§
Structs§
- Layer
Base - The
LayerBasestruct is a base representation of a neural network layer, essentially binding an activation function,F, to a set of parameters,ParamsBase<S, D>. - Linear
- ReLU
- Sigmoid
- Tanh
Traits§
- Activator
- The
Activatortrait defines a method for applying an activation function to an input tensor. - Activator
Gradient - The
ActivatorGradienttrait extends theActivatortrait to include a method for computing the gradient of the activation function. - Layer
- A generic trait defining the composition of a layer within a neural network.
- Layer
Ext - The
LayerExttrait extends the baseLayertrait with additional methods that are commonly used in neural network layers. It provides methods for setting parameters, performing backward propagation of errors, and completing a forward pass through the layer.
Type Aliases§
- Linear
Layer - A type alias for a
LayerBaseconfigured with aLinearactivation function. - Relu
Layer - A type alias for a
LayerBaseconfigured with aReLUactivation function. - Sigmoid
Layer - A type alias for a
LayerBaseconfigured with aSigmoidactivation function. - Tanh
Layer - A type alias for a
LayerBaseconfigured with aTanhactivation function.