Table of Contents

Namespace NeuralNetworks.Operations.ActivationFunctions

Classes

ActivationFunction<TIn, TOut>

Defines an abstract 2D activation function operation applied element-wise to two-dimensional data.

BipolarSigmoid

Represents a bipolar sigmoid activation operation that applies a scaled sigmoid function shifted to the range [-0.5, 0.5].

LeakyReLU2D
LeakyReLU3D
LeakyReLU4D
Linear

"Identity" activation function

ReLU2D
ReLU3D
ReLU4D
Sigmoid

Sigmoid activation function.

Softplus

Softplus is a smooth approximation of the ReLU (Rectified Linear Unit) activation function. It is defined as f(x) = log(1 + exp(x)) and is differentiable everywhere, making it suitable for gradient-based optimization methods.

Tanh2D
Tanh4D