Detailed Description

GNeuralNet contains GLayers stacked upon each other. GLayer contains GBlocks concatenated beside each other. (GNeuralNet is a type of GBlock.) Each GBlock is an array of differentiable network units (artificial neurons). The user must add at least one GBlock to each GLayer.

#include <GNeuralNet.h>

Public Member Functions
	GLayer ()

	GLayer (GDomNode *pNode)

virtual	~GLayer ()

void	add (GBlock *pBlock, size_t inPos=0)
	Adds a block of network units (artificial neurons) to this layer. inPos specifies the index of the first output from the previous layer that will feed into this block of units. More...

void	backProp (GContextLayer &ctx, const GVec &input, const GVec &output, const GVec &outBlame, GVec &inBlame) const
	Backpropagates the blame through the layer that was used to construct this object. More...

GBlock &	block (size_t i)
	Returns a reference to the specified block. More...

const GBlock &	block (size_t i) const

size_t	blockCount () const
	Returns the number of blocks in this layer. More...

void	copyWeights (const GLayer *pOther)
	Copies the weights from pOther. (Assumes pOther has the same structure.) More...

void	diminishWeights (double amount, bool diminishBiases)
	Moves all weights by a constant amount toward 0. More...

void	forwardProp (GContextLayer &ctx, const GVec &input, GVec &output) const
	Feeds input forward through the layer that was used to construct this object. More...

void	forwardProp_training (GContextLayer &ctx, const GVec &input, GVec &output) const
	Identical to forwardProp, except recurrent blocks additionally propagate through time during training. More...

size_t	inputs () const
	Returns the number of inputs that this layer consumes. More...

void	maxNorm (double min, double max)
	Clips the magnitude of the weight vector in each network unit to fall within the specified range. More...

GContextLayer *	newContext (GRand &rand) const
	Allocates a new GContextLayer object, which can be used to train or predict with this layer. (Behavior is undefined if you add any blocks after you call newContext.) More...

size_t	outputs () const
	Returns the number of outputs that this layer produces. More...

void	perturbWeights (GRand &rand, double deviation)
	Perturbs all the weights in this layer by adding Gaussian noise with the specified deviation. More...

void	recount ()
	Recounts the number of inputs, outputs, and weights in this layer. More...

void	resetWeights (GRand &rand)
	Resets the weights in all of the blocks in this layer. More...

void	scaleWeights (double factor, bool scaleBiases)
	Scales all the weights in this layer. More...

GDomNode *	serialize (GDom *pDoc) const
	Marshal this object into a dom node. More...

void	step (double learningRate, const GVec &gradient)
	Take a step to descend the gradient by updating the weights. More...

void	updateGradient (GContextLayer &ctx, const GVec &input, const GVec &outBlame, GVec &gradient) const
	Updates the gradient for the layer that was used to construct this object. More...

size_t	vectorToWeights (const double *pVector)
	Unmarshals all the weights in this layer from a vector. More...

size_t	weightCount () const
	Returns the total number of weights in this layer. More...

size_t	weightsToVector (double *pOutVector) const
	Marshals all the weights in this layer into a vector. More...

Protected Attributes
std::vector< GBlock * >	m_blocks

size_t	m_inputs

size_t	m_outputs

size_t	m_weightCount

Constructor & Destructor Documentation

GClasses::GLayer::GLayer ( )

GClasses::GLayer::GLayer ( GDomNode * pNode )

virtual GClasses::GLayer::~GLayer ( )

virtual

Member Function Documentation

void GClasses::GLayer::add	(	GBlock *	pBlock,
		size_t	inPos = `0`
	)

Adds a block of network units (artificial neurons) to this layer. inPos specifies the index of the first output from the previous layer that will feed into this block of units.

void GClasses::GLayer::backProp	(	GContextLayer &	ctx,
		const GVec &	input,
		const GVec &	output,
		const GVec &	outBlame,
		GVec &	inBlame
	)		const

Backpropagates the blame through the layer that was used to construct this object.

GBlock& GClasses::GLayer::block ( size_t i )

inline

Returns a reference to the specified block.

const GBlock& GClasses::GLayer::block ( size_t i ) const

inline

size_t GClasses::GLayer::blockCount ( ) const

inline

Returns the number of blocks in this layer.

void GClasses::GLayer::copyWeights ( const GLayer * pOther )

Copies the weights from pOther. (Assumes pOther has the same structure.)

void GClasses::GLayer::diminishWeights	(	double	amount,
		bool	diminishBiases
	)

Moves all weights by a constant amount toward 0.

void GClasses::GLayer::forwardProp	(	GContextLayer &	ctx,
		const GVec &	input,
		GVec &	output
	)		const

Feeds input forward through the layer that was used to construct this object.

void GClasses::GLayer::forwardProp_training	(	GContextLayer &	ctx,
		const GVec &	input,
		GVec &	output
	)		const

Identical to forwardProp, except recurrent blocks additionally propagate through time during training.

size_t GClasses::GLayer::inputs ( ) const

Returns the number of inputs that this layer consumes.

void GClasses::GLayer::maxNorm	(	double	min,
		double	max
	)

Clips the magnitude of the weight vector in each network unit to fall within the specified range.

GContextLayer* GClasses::GLayer::newContext ( GRand & rand ) const

Allocates a new GContextLayer object, which can be used to train or predict with this layer. (Behavior is undefined if you add any blocks after you call newContext.)

size_t GClasses::GLayer::outputs ( ) const

Returns the number of outputs that this layer produces.

void GClasses::GLayer::perturbWeights	(	GRand &	rand,
		double	deviation
	)

Perturbs all the weights in this layer by adding Gaussian noise with the specified deviation.

void GClasses::GLayer::recount ( )

Recounts the number of inputs, outputs, and weights in this layer.

void GClasses::GLayer::resetWeights ( GRand & rand )

Resets the weights in all of the blocks in this layer.

void GClasses::GLayer::scaleWeights	(	double	factor,
		bool	scaleBiases
	)

Scales all the weights in this layer.

GDomNode* GClasses::GLayer::serialize ( GDom * pDoc ) const

Marshal this object into a dom node.

void GClasses::GLayer::step	(	double	learningRate,
		const GVec &	gradient
	)

Take a step to descend the gradient by updating the weights.

void GClasses::GLayer::updateGradient	(	GContextLayer &	ctx,
		const GVec &	input,
		const GVec &	outBlame,
		GVec &	gradient
	)		const

Updates the gradient for the layer that was used to construct this object.

size_t GClasses::GLayer::vectorToWeights ( const double * pVector )

Unmarshals all the weights in this layer from a vector.

size_t GClasses::GLayer::weightCount ( ) const

Returns the total number of weights in this layer.

size_t GClasses::GLayer::weightsToVector ( double * pOutVector ) const

Marshals all the weights in this layer into a vector.

Member Data Documentation

std::vector<GBlock*> GClasses::GLayer::m_blocks

protected

size_t GClasses::GLayer::m_inputs

protected

size_t GClasses::GLayer::m_outputs

protected

size_t GClasses::GLayer::m_weightCount

protected

Detailed Description

Public Member Functions

Protected Attributes

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation