Detailed Description

Consumes n values and produces a big vector in the form of two vectors (concatenated together) whose corresponding values form all pairs of inputs, plus each input is also paired with each of "lo" and "hi". Example: If the input is {1,2,3}, then the output will be {1,1,1,1,2,2,2,3,3, 2,3,lo,hi,3,lo,hi,lo,hi}. Thus, if there are n inputs, there will be n(n-1)+4n outputs.

#include <GBlock.h>

Inheritance diagram for GClasses::GBlockAllPairings:

Public Member Functions
	GBlockAllPairings (size_t inputs, double lo, double hi)
	General-purpose constructor. More...

	GBlockAllPairings (GDomNode *pNode)
	Deserializing constructor. More...

	~GBlockAllPairings ()

virtual void	backProp (GContext &ctx, const GVec &input, const GVec &output, const GVec &outBlame, GVec &inBlame) const override
	Evaluates outBlame, and adds to inBlame. (Note that it "adds to" the inBlame because multiple blocks may fork from a common source.) More...

size_t	findSource (size_t outputUnit)
	Returns the input unit that is connected with the specifed output unit. Returns inputs() for "lo", and inputs()+1 for "hi". (The current implementation is not very efficient.) More...

virtual void	forwardProp (GContext &ctx, const GVec &input, GVec &output) const override
	Evaluate the input, set the output. More...

virtual size_t	inputs () const override
	Returns the number of inputs this block consumes. More...

virtual std::string	name () const override
	Returns the name of this block. More...

virtual size_t	outputs () const override
	Returns the number of outputs this block produces. More...

virtual void	resize (size_t inputs, size_t outputs) override
	Resizes this block. outputs must be 2*inputs. More...

virtual GDomNode *	serialize (GDom *pDoc) const override
	Marshall this block into a DOM. More...

virtual BlockType	type () const override
	Returns the type of this block. More...

Public Member Functions inherited from GClasses::GBlockWeightless
	GBlockWeightless ()

	GBlockWeightless (GDomNode *pNode)

virtual	~GBlockWeightless ()

virtual void	copyWeights (const GBlock *pSource) override
	Copy the weights from pSource to this block. (Assumes pSource is the same type of block.) More...

virtual void	diminishWeights (double amount, bool regularizeBiases) override
	Moves all weights in the direction of zero by the specified amount. More...

virtual void	maxNorm (double min, double max) override
	Scales weights if necessary such that the manitude of the weights (not including the bias) feeding into each unit are >= min and <= max. More...

virtual void	perturbWeights (GRand &rand, double deviation) override
	Perturbs the weights that feed into the specifed units with Gaussian noise. The default values apply the perturbation to all units. More...

virtual void	resetWeights (GRand &rand) override
	Initialize the weights, usually with small random values. More...

virtual void	scaleWeights (double factor, bool scaleBiases) override
	Multiplies all the weights by the specified factor. More...

virtual void	step (double learningRate, const GVec &gradient) override
	Add the weight and bias gradient to the weights. More...

virtual void	updateGradient (GContext &ctx, const GVec &input, const GVec &outBlame, GVec &gradient) const override
	Evaluate the input and outBlame, update the gradient for updating the weights by gradient descent. More...

virtual size_t	vectorToWeights (const double *pVector) override
	Deserialize from a vector to the weights in this block. Return the number of elements consumed. More...

virtual size_t	weightCount () const override
	Returns the number of double-precision elements necessary to serialize the weights of this block into a vector. More...

virtual size_t	weightsToVector (double *pOutVector) const override
	Serialize the weights in this block into a vector. Return the number of elements written. More...

Public Member Functions inherited from GClasses::GBlock
	GBlock ()

	GBlock (GDomNode *pNode)

virtual	~GBlock ()

virtual bool	elementWise () const
	Returns true iff this block operates only on individual elements. More...

size_t	inPos () const
	Returns the offset in the previous layer's output where values are fed as input to this block. More...

virtual bool	isRecurrent () const
	Returns true iff this block is recurrent. More...

void	setInPos (size_t n)
	Sets the starting offset in the previous layer's output where values will be fed as input to this block. More...

virtual std::string	to_str () const
	Returns a string representation of this block. More...

virtual bool	usesGPU ()
	Returns true iff this block does its computations in parallel on a GPU. More...

Protected Attributes
double	m_hi

size_t	m_inputCount

double	m_lo

Protected Attributes inherited from GClasses::GBlock
size_t	m_inPos

Additional Inherited Members
Public Types inherited from GClasses::GBlock
Static Public Member Functions inherited from GClasses::GBlock
static GBlock *	deserialize (GDomNode *pNode)
	Unmarshalls the specified DOM node into a block object. More...

Protected Member Functions inherited from GClasses::GBlock
GDomNode *	baseDomNode (GDom *pDoc) const

void	basicTest ()
	Exercises some basic functionality that all blocks have in common. More...

Constructor & Destructor Documentation

GClasses::GBlockAllPairings::GBlockAllPairings	(	size_t	inputs,
		double	lo,
		double	hi
	)

General-purpose constructor.

GClasses::GBlockAllPairings::GBlockAllPairings ( GDomNode * pNode )

Deserializing constructor.

GClasses::GBlockAllPairings::~GBlockAllPairings ( )

Member Function Documentation

virtual void GClasses::GBlockAllPairings::backProp	(	GContext &	ctx,
		const GVec &	input,
		const GVec &	output,
		const GVec &	outBlame,
		GVec &	inBlame
	)		const

overridevirtual

Evaluates outBlame, and adds to inBlame. (Note that it "adds to" the inBlame because multiple blocks may fork from a common source.)

Implements GClasses::GBlock.

size_t GClasses::GBlockAllPairings::findSource ( size_t outputUnit )

Returns the input unit that is connected with the specifed output unit. Returns inputs() for "lo", and inputs()+1 for "hi". (The current implementation is not very efficient.)