Dense.hpp File Reference

Dense (fully-connected) layer for FlexNN::Layers. More...

#include <string>
#include <utility>
#include <Eigen/Dense>
#include "LayerTypes.hpp"
#include "activations/Activation.hpp"
#include "activations/ActivationParameters.hpp"

Include dependency graph for Dense.hpp:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	FlexNN::Layers::Dense
	Fully-connected layer: Z = W*X + b, A = act(Z). More...

Namespaces
namespace	FlexNN
	Namespace for the FlexNN neural network library.
namespace	FlexNN::Layers

Detailed Description

Dense (fully-connected) layer for FlexNN::Layers.

Each Dense instance owns its weights W [out×in] and biases b [out] as double (Eigen MatrixXd/VectorXd) for training. Export via ModelIO casts to float32 row-major. The layer is stateless aside from its parameters and activation — no virtual, no heap beyond Eigen.