mnist_mlp.hpp File Reference

#include <algorithm>
#include <cmath>
#include <cypress/cypress.hpp>
#include "helper_functions.hpp"

Go to the source code of this file.

Classes
class	MNIST::MSE
	Root Mean Squared Error. More...
class	MNIST::CatHinge
	Categorical hinge loss. Use if weights are restricted to be >0. More...
class	MNIST::ReLU
	ActivationFunction ReLU: Rectified Linear Unit. More...
class	MNIST::NoConstraint
	Constraint for weights in neural network: No constraint. More...
class	MNIST::PositiveWeights
	Constraint for weights in neural network: Only weights >0. More...
class	MNIST::PositiveLimitedWeights
class	MNIST::MLPBase
	Base class for Multi Layer Networks (–> currently Perceptron only). Allows us to use polymorphism with templated class. More...
class	MNIST::MLP< Loss, ActivationFunction, Constraint >
	The standard densely connected multilayer Perceptron. Template arguments provide the loss function, the activation function of neurons (experimental) and a possible constraint for the weights. More...

Namespaces
	MNIST