|
FlexNN 1
Fully connected neural network built from scratch with flexible n-layer design and multiple activations.
|
ReLU activation — max(0, z) forward, (z>0) backward. More...
#include <algorithm>#include <Eigen/Dense>

Go to the source code of this file.
Namespaces | |
| namespace | FlexNN |
| Namespace for the FlexNN neural network library. | |
| namespace | FlexNN::Activations |
| namespace | FlexNN::Activations::detail |
Functions | |
| Eigen::MatrixXd | FlexNN::Activations::detail::relu_forward (const Eigen::MatrixXd &Z) |
| ReLU forward: A = max(0, Z) elementwise. | |
| Eigen::MatrixXd | FlexNN::Activations::detail::relu_backward (const Eigen::MatrixXd &dA, const Eigen::MatrixXd &Z, const Eigen::MatrixXd &) noexcept |
| ReLU backward: dZ = dA * (Z > 0). | |
ReLU activation — max(0, z) forward, (z>0) backward.