FlexNN 1
Fully connected neural network built from scratch with flexible n-layer design and multiple activations.
|
This is the complete list of members for FlexNN::Layer, including all inherited members.
backward(const Eigen::MatrixXd &nextW, const Eigen::MatrixXd &nextdZ, const Eigen::MatrixXd &currZ) | FlexNN::Layer | |
forward(const Eigen::MatrixXd &input) | FlexNN::Layer | |
getBiases() const | FlexNN::Layer | inline |
getWeights() const | FlexNN::Layer | inline |
Layer(int inputSize, int outputSize, const std::string &activationFunction="relu") | FlexNN::Layer | inline |
updateWeights(const Eigen::MatrixXd &dW, const Eigen::VectorXd &db, double learningRate) | FlexNN::Layer | inline |