aureservoir::TrainBase< T > Class Template Reference

#include <train.h>

Inheritance diagram for aureservoir::TrainBase< T >:

[legend]

Collaboration diagram for aureservoir::TrainBase< T >:

[legend]

---

Detailed Description

template<typename T>
class aureservoir::TrainBase< T >

This class is an abstract base class for all different kinds of training algorithms. The idea behind this system is that the algorithms can be exchanged at runtime (strategy pattern).

Simply derive from this class if you want to add a new algorithm.

Public Member Functions
	TrainBase (ESN< T > *esn)
virtual	~TrainBase ()
virtual void	train (const typename ESN< T >::DEMatrix &in, const typename ESN< T >::DEMatrix &out, int washout)=0 throw (AUExcept)
Protected Member Functions
void	clearData ()
class TrainBase Implementation
void	checkParams (const typename ESN< T >::DEMatrix &in, const typename ESN< T >::DEMatrix &out, int washout) throw (AUExcept)
void	collectStates (const typename ESN< T >::DEMatrix &in, const typename ESN< T >::DEMatrix &out, int washout)
void	squareStates ()
Protected Attributes
ESN< T > *	esn_
ESN< T >::DEMatrix	M
ESN< T >::DEMatrix	O

---

Constructor & Destructor Documentation

template<typename T>

aureservoir::TrainBase< T >::TrainBase

(

ESN< T > *

esn

)

[inline]

Constructor.

template<typename T>

virtual aureservoir::TrainBase< T >::~TrainBase

(

)

[inline, virtual]

Destructor.

---

Member Function Documentation

template<typename T>

virtual void aureservoir::TrainBase< T >::train	(	const typename ESN< T >::DEMatrix &	in,
		const typename ESN< T >::DEMatrix &	out,
		int	washout
	)			throw (AUExcept) [pure virtual]

training algorithm

Parameters:

	in	matrix of input values (inputs x timesteps)
	out	matrix of desired output values (outputs x timesteps) for teacher forcing
	washout	washout time in samples, used to get rid of the transient dynamics of the network starting state

Implemented in aureservoir::TrainPI< T >, aureservoir::TrainLS< T >, aureservoir::TrainRidgeReg< T >, and aureservoir::TrainDSPI< T >.

template<typename T>

void aureservoir::TrainBase< T >::checkParams	(	const typename ESN< T >::DEMatrix &	in,
		const typename ESN< T >::DEMatrix &	out,
		int	washout
	)			throw (AUExcept) [inline, protected]

check parameters

template<typename T>

void aureservoir::TrainBase< T >::collectStates	(	const typename ESN< T >::DEMatrix &	in,
		const typename ESN< T >::DEMatrix &	out,
		int	washout
	)			[inline, protected]

collect network states with simulation algorithm

template<typename T>

void aureservoir::TrainBase< T >::squareStates

(

)

[inline, protected]

squares states for SIM_SQUARE

template<typename T>

void aureservoir::TrainBase< T >::clearData

(

)

[inline, protected]

frees allocated data for M and O

---

Field Documentation

template<typename T>

ESN<T>* aureservoir::TrainBase< T >::esn_ [protected]

reference to the data of the network

template<typename T>

ESN<T>::DEMatrix aureservoir::TrainBase< T >::M [protected]

matrix for network states and inputs over all timesteps

template<typename T>

ESN<T>::DEMatrix aureservoir::TrainBase< T >::O [protected]

matrix for outputs over all timesteps

---

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

• train.h
• train.hpp

---