net::Trainer Class Reference

Trains neural networks. More...

#include <Trainer.h>

Inherited by net::SGDTrainer.

Public Member Functions
virtual double	train (net::NeuralNet *network, const std::vector< std::vector< double > > &input, const std::vector< std::vector< double > > &correctOutput)=0
	Trains a neural network on a training set. More...
virtual void	store (std::ofstream *output)=0
	Stores a Trainer object using specified stream. More...
std::vector< std::vector < std::vector< std::vector < double > > > >	getGradients ()
std::vector< std::vector < std::vector< std::vector < double > > > >	getWeightChanges ()
std::vector< std::vector < std::vector< double > > >	getInitialWeights ()
std::vector< std::vector < std::vector< double > > >	getFinalWeights ()

Protected Attributes
std::vector< std::vector < std::vector< std::vector < double > > > >	gradients
std::vector< std::vector < std::vector< std::vector < double > > > >	weightChanges
std::vector< std::vector < std::vector< double > > >	initialWeights
std::vector< std::vector < std::vector< double > > >	finalWeights

Detailed Description

Trains neural networks.

Member Function Documentation

std::vector< std::vector< std::vector<double> > > net::Trainer::getFinalWeights ( )

inline

std::vector< std::vector< std::vector< std::vector<double> > > > net::Trainer::getGradients ( )

inline

std::vector< std::vector< std::vector<double> > > net::Trainer::getInitialWeights ( )

inline

std::vector< std::vector< std::vector< std::vector<double> > > > net::Trainer::getWeightChanges ( )

inline

virtual void net::Trainer::store ( std::ofstream *  output )

pure virtual

Stores a Trainer object using specified stream.

Parameters

output

pointer to the output stream which the neural network will be written to

Implemented in net::SGDTrainer, net::Backpropagation, and net::Adadelta.

virtual double net::Trainer::train ( net::NeuralNet *  network, const std::vector< std::vector< double > > &  input, const std::vector< std::vector< double > > &  correctOutput  )

pure virtual

Trains a neural network on a training set.

Edits the weights of the neural network until its error in predicting the correctOutput of each input reaches the value of targetErrorLevel or the number of training cycles reaches the value of maximumIterations.

Parameters

network	the neural network to be trained
input	a vector of neural network inputs; each element in input, should have a corresponding output in correctOutput
correctOutput	network is trained to output an element of correctOutput when fed a corresponding element of the input vector

Implemented in net::SGDTrainer.

Member Data Documentation

std::vector< std::vector< std::vector<double> > > net::Trainer::finalWeights

protected

std::vector< std::vector< std::vector< std::vector<double> > > > net::Trainer::gradients

protected

std::vector< std::vector< std::vector<double> > > net::Trainer::initialWeights

protected

std::vector< std::vector< std::vector< std::vector<double> > > > net::Trainer::weightChanges

protected

---

The documentation for this class was generated from the following file:

• /home/truell20/Documents/Fido/Fido/include/Trainer.h