Implements k-step Contrastive Divergence described by Hinton et al. (2006). More...
#include <shark/Unsupervised/RBM/GradientApproximations/ContrastiveDivergence.h>
Public Types | |
typedef Operator::RBM | RBM |
Public Types inherited from shark::AbstractObjectiveFunction< PointType, ResultT > | |
enum | Feature { HAS_VALUE = 1, HAS_FIRST_DERIVATIVE = 2, HAS_SECOND_DERIVATIVE = 4, CAN_PROPOSE_STARTING_POINT = 8, IS_CONSTRAINED_FEATURE = 16, HAS_CONSTRAINT_HANDLER = 32, CAN_PROVIDE_CLOSEST_FEASIBLE = 64, IS_THREAD_SAFE = 128, IS_NOISY = 256 } |
List of features that are supported by an implementation. More... | |
typedef PointType | SearchPointType |
typedef ResultT | ResultType |
typedef boost::mpl::if_< std::is_arithmetic< ResultT >, SearchPointType, RealMatrix >::type | FirstOrderDerivative |
typedef TypedFlags< Feature > | Features |
This statement declares the member m_features. See Core/Flags.h for details. More... | |
typedef TypedFeatureNotAvailableException< Feature > | FeatureNotAvailableException |
Public Member Functions | |
ContrastiveDivergence (RBM *rbm) | |
The constructor. More... | |
std::string | name () const |
From INameable: return the class name. More... | |
void | setData (UnlabeledData< RealVector > const &data) |
Sets the training batch. More... | |
void | setK (unsigned int k) |
Sets the value of k- the number of steps of the Gibbs Chain. More... | |
SearchPointType | proposeStartingPoint () const |
Proposes a starting point in the feasible search space of the function. More... | |
std::size_t | numberOfVariables () const |
Returns the number of variables of the RBM. More... | |
std::size_t | numBatches () const |
Returns the number of batches of the dataset that are used in every iteration. More... | |
std::size_t & | numBatches () |
Returns a reference to the number of batches of the dataset that are used in every iteration. More... | |
void | setRegularizer (double factor, SingleObjectiveFunction *regularizer) |
double | evalDerivative (SearchPointType const ¶meter, FirstOrderDerivative &derivative) const |
Gives the CD-k approximation of the log-likelihood gradient. More... | |
Public Member Functions inherited from shark::AbstractObjectiveFunction< PointType, ResultT > | |
const Features & | features () const |
virtual void | updateFeatures () |
bool | hasValue () const |
returns whether this function can calculate it's function value More... | |
bool | hasFirstDerivative () const |
returns whether this function can calculate the first derivative More... | |
bool | hasSecondDerivative () const |
returns whether this function can calculate the second derivative More... | |
bool | canProposeStartingPoint () const |
returns whether this function can propose a starting point. More... | |
bool | isConstrained () const |
returns whether this function can return More... | |
bool | hasConstraintHandler () const |
returns whether this function can return More... | |
bool | canProvideClosestFeasible () const |
Returns whether this function can calculate thee closest feasible to an infeasible point. More... | |
bool | isThreadSafe () const |
Returns true, when the function can be usd in parallel threads. More... | |
bool | isNoisy () const |
Returns true, when the function can be usd in parallel threads. More... | |
AbstractObjectiveFunction () | |
Default ctor. More... | |
virtual | ~AbstractObjectiveFunction () |
Virtual destructor. More... | |
virtual void | init () |
void | setRng (random::rng_type *rng) |
Sets the Rng used by the objective function. More... | |
virtual bool | hasScalableDimensionality () const |
virtual void | setNumberOfVariables (std::size_t numberOfVariables) |
Adjusts the number of variables if the function is scalable. More... | |
virtual std::size_t | numberOfObjectives () const |
virtual bool | hasScalableObjectives () const |
virtual void | setNumberOfObjectives (std::size_t numberOfObjectives) |
Adjusts the number of objectives if the function is scalable. More... | |
std::size_t | evaluationCounter () const |
Accesses the evaluation counter of the function. More... | |
AbstractConstraintHandler< SearchPointType > const & | getConstraintHandler () const |
Returns the constraint handler of the function if it has one. More... | |
virtual bool | isFeasible (const SearchPointType &input) const |
Tests whether a point in SearchSpace is feasible, e.g., whether the constraints are fulfilled. More... | |
virtual void | closestFeasible (SearchPointType &input) const |
If supported, the supplied point is repaired such that it satisfies all of the function's constraints. More... | |
virtual ResultType | eval (SearchPointType const &input) const |
Evaluates the objective function for the supplied argument. More... | |
ResultType | operator() (SearchPointType const &input) const |
Evaluates the function. Useful together with STL-Algorithms like std::transform. More... | |
virtual ResultType | evalDerivative (SearchPointType const &input, SecondOrderDerivative &derivative) const |
Evaluates the objective function and calculates its gradient. More... | |
Public Member Functions inherited from shark::INameable | |
virtual | ~INameable () |
Additional Inherited Members | |
Protected Member Functions inherited from shark::AbstractObjectiveFunction< PointType, ResultT > | |
void | announceConstraintHandler (AbstractConstraintHandler< SearchPointType > const *handler) |
helper function which is called to announce the presence of an constraint handler. More... | |
Protected Attributes inherited from shark::AbstractObjectiveFunction< PointType, ResultT > | |
Features | m_features |
std::size_t | m_evaluationCounter |
Evaluation counter, default value: 0. More... | |
AbstractConstraintHandler< SearchPointType > const * | m_constraintHandler |
random::rng_type * | mep_rng |
Implements k-step Contrastive Divergence described by Hinton et al. (2006).
k-step Contrastive Divergence approximates the gradient by initializing a Gibbs chain with a training example and run it for k steps. The sample gained after k steps than samples is than used to approximate the mean of the RBM distribution in the gradient.
Definition at line 44 of file ContrastiveDivergence.h.
typedef Operator::RBM shark::ContrastiveDivergence< Operator >::RBM |
Definition at line 46 of file ContrastiveDivergence.h.
|
inline |
The constructor.
rbm | pointer to the RBM which shell be trained |
Definition at line 51 of file ContrastiveDivergence.h.
References shark::AbstractObjectiveFunction< PointType, ResultT >::CAN_PROPOSE_STARTING_POINT, shark::AbstractObjectiveFunction< PointType, ResultT >::HAS_FIRST_DERIVATIVE, shark::AbstractObjectiveFunction< PointType, ResultT >::HAS_VALUE, shark::AbstractObjectiveFunction< PointType, ResultT >::m_features, shark::TypedFlags< Flag >::reset(), and SHARK_ASSERT.
|
inlinevirtual |
Gives the CD-k approximation of the log-likelihood gradient.
parameter | the actual parameters of the RBM |
derivative | holds later the CD-k approximation of the log-likelihood gradient |
Reimplemented from shark::AbstractObjectiveFunction< PointType, ResultT >.
Definition at line 113 of file ContrastiveDivergence.h.
References shark::Data< Type >::batch(), shark::batchEnd(), shark::ContrastiveDivergence< Operator >::numBatches(), shark::Data< Type >::numberOfBatches(), SHARK_NUM_THREADS, SHARK_PARALLEL_FOR, and shark::shuffle().
|
inlinevirtual |
From INameable: return the class name.
Reimplemented from shark::INameable.
Definition at line 62 of file ContrastiveDivergence.h.
|
inline |
Returns the number of batches of the dataset that are used in every iteration.
If it is less than all batches, the batches are chosen at random. if it is 0, all batches are used
Definition at line 93 of file ContrastiveDivergence.h.
Referenced by shark::ContrastiveDivergence< Operator >::evalDerivative().
|
inline |
Returns a reference to the number of batches of the dataset that are used in every iteration.
If it is less than all batches, the batches are chosen at random.if it is 0, all batches are used.
Definition at line 100 of file ContrastiveDivergence.h.
|
inlinevirtual |
Returns the number of variables of the RBM.
Implements shark::AbstractObjectiveFunction< PointType, ResultT >.
Definition at line 86 of file ContrastiveDivergence.h.
|
inlinevirtual |
Proposes a starting point in the feasible search space of the function.
FeatureNotAvailableException | in the default implementation and if a function does not support this feature. |
Reimplemented from shark::AbstractObjectiveFunction< PointType, ResultT >.
Definition at line 79 of file ContrastiveDivergence.h.
|
inline |
Sets the training batch.
data | the batch of training data |
Definition at line 68 of file ContrastiveDivergence.h.
Referenced by main(), and trainRBM().
|
inline |
Sets the value of k- the number of steps of the Gibbs Chain.
k | the number of steps |
Definition at line 75 of file ContrastiveDivergence.h.
Referenced by main(), and trainRBM().
|
inline |
Definition at line 104 of file ContrastiveDivergence.h.
Referenced by trainRBM().