Main Page | Namespace List | Class Hierarchy | Alphabetical List | Class List | File List | Namespace Members | Class Members | File Members

PLearn::EntropyContrast Class Reference

#include <EntropyContrast.h>

Inheritance diagram for PLearn::EntropyContrast:

Inheritance graph
[legend]
Collaboration diagram for PLearn::EntropyContrast:

Collaboration graph
[legend]
List of all members.

Public Member Functions

 EntropyContrast ()
virtual void build ()
 simply calls inherited::build() then build_()

virtual void makeDeepCopyFromShallowCopy (map< const void *, void * > &copies)
 Transforms a shallow copy into a deep copy.

 PLEARN_DECLARE_OBJECT (EntropyContrast)
virtual int outputsize () const
 returns the size of this learner's output, (which typically may depend on its inputsize(), targetsize() and set options)

virtual void forget ()
 (Re-)initializes the PLearner in its fresh state (that state may depend on the 'seed' option) And sets 'stage' back to 0 (this is the stage of a fresh learner!)

virtual void train ()
 The role of the train method is to bring the learner up to stage==nstages, updating the train_stats collector with training costs measured on-line in the process.

virtual void computeOutput (const Vec &input, Vec &output) const
 Computes the output from the input.

void reconstruct (const Vec &output, Vec &input) const
 Reconstructs an input from a (possibly partial) output (i.e. the first few princial components kept).

virtual void computeCostsFromOutputs (const Vec &input, const Vec &output, const Vec &target, Vec &costs) const
 Computes the costs from already computed output.

virtual TVec< string > getTestCostNames () const
 Returns [ "squared_reconstruction_error" ].

virtual TVec< string > getTrainCostNames () const
 No trian costs are computed for this learner.


Public Attributes

string cost_real
string cost_gen
string cost_extra
string gen_method
string evaluation_method
int nconstraints
int inputsize
 The number of constraints.

real learning_rate
real decay_factor
 the learning rate

real weight_real
 the decay factor of the learning rate

real weight_gen
 the decay factor of the learning rate

real weight_extra
 the decay factor of the learning rate

real weight_decay_output
real weight_decay_hidden
int n_seen_examples
real starting_learning_rate

Static Protected Member Functions

void declareOptions (OptionList &ol)
 Declares this class' options.


Private Types

typedef PLearner inherited

Private Member Functions

void build_ ()
 This does the actual building.

string getInfo ()
void initialize_NNcontinuous ()
 Initialize all the data structures for the NNet.

void update_NNcontinuous ()
 update the parameters of the NNet from the regular cost

void computeNNcontinuous_hidden (const Vec &input_units, Vec &hidden_units)
 compute the hidden units of the NNet given the input

void computeNNcontinuous_constraints (Vec &hidden_units, Vec &output_units)
 Compute the output units given the hidden units.

void get_NNcontinuous_output (const Vec &x, Vec &f_x, Vec &z_x)
 Compute the output units and also the hidden units given the input.

void update_mu_sigma_f (const Vec &f_x, Vec &mu, Vec &sigma)
 Given the output of the NNet it updates the running averages(mu, variance).

void update_alpha (int stage, int current_input_index)
 Update the weight of a sample(alpha).

void compute_diversity_cost (const Vec &f_x, const Vec &cost, Vec &grad_C_extra_cost_wrt_f_x)
 Compute the cost and the gradiant for the diversity cost given by C_i = sum_j<i {cov((f_i)^2,(f_j)^2)}.

void get_real_grad_variance_wrt_f (const Vec &f_x, Vec &grad)
 Compute d Var(f_x) / df_x.

void get_gen_grad_variance_wrt_f (const Vec &f_x, Vec &grad)
 Compute d Var(f_x_hat) / df_x_hat.

void set_NNcontinuous_gradient (Vec &grad_C_real_wrt_f_x, Mat &grad_H_f_x_wrt_w, Mat &grad_H_f_x_wrt_v, Vec &z_x, Vec &x, Vec &grad_H_f_x_wrt_bias_output, Vec &grad_H_f_x_wrt_bias_hidden)
 Compute all the gradiants wrt to the parameters of the neural network.

void gen_normal_0_1 (Vec &output)
 Fill a vector with numbers from a gaussian having mu=0 , and sigma=1 This can be used for the generataion of the data.

void set_NNcontinuous_gradient_from_extra_cost (Mat &grad_C_wrt_df_dx, const Vec &input)
 do the bprop step for NNet, compute all the gradiants

void compute_df_dx (Mat &df_dx, const Vec &input)
 Compute df/dx, given x(input).

void compute_extra_grad_wrt_df_dx (Mat &grad_C_wrt_df_dx)
 compute the grad extra_cost wrt df_dx

void update_NNcontinuous_from_extra_cost ()
 update the parameters of the NNet from the extra cost given by the derivative(angle) cost


Private Attributes

int n
int evaluate_every_n_epochs
bool evaluate_first_epoch
Mat w
Mat v
Vec x
Vec f_x
Vec grad_C_real_wrt_f_x
Vec grad_C_extra_cost_wrt_f_x
Vec x_hat
Vec f_x_hat
Vec grad_C_generated_wrt_f_x_hat
VMat test_set
VMat validation_set
real alpha
int nhidden
Vec mu_f
 the number of hidden units, in the one existing hidden layer

Vec sigma_f
Vec mu_f_hat
Vec sigma_f_hat
Vec mu_f_square
Vec sigma_f_square
Mat grad_H_f_x_wrt_w
Mat grad_H_f_x_hat_wrt_w
Mat grad_H_f_x_wrt_v
Mat grad_H_f_x_hat_wrt_v
Vec grad_H_f_x_wrt_bias_output
Vec grad_H_f_x_wrt_bias_hidden
Vec grad_H_f_x_hat_wrt_bias_output
Vec grad_H_f_x_hat_wrt_bias_hidden
Mat grad_H_g_wrt_w
Vec sigma_g
Vec mu_g
Vec g_x
Vec bias_hidden
Vec z_x
Vec z_x_hat
Vec bias_output
Vec full_sum
real full
Mat df_dx
Mat grad_C_wrt_df_dx
Mat grad_extra_wrt_w
Mat grad_extra_wrt_v
Vec grad_extra_wrt_bias_hidden
Vec grad_extra_wrt_bias_output

Member Typedef Documentation

typedef PLearner PLearn::EntropyContrast::inherited [private]
 

Reimplemented from PLearn::PLearner.

Definition at line 65 of file EntropyContrast.h.

Constructor & Destructor Documentation

PLearn::EntropyContrast::EntropyContrast (   ) 
 

Definition at line 49 of file EntropyContrast.cc.

References alpha, decay_factor, evaluate_every_n_epochs, evaluate_first_epoch, evaluation_method, learning_rate, n, nconstraints, nhidden, weight_extra, weight_gen, and weight_real.

Member Function Documentation

void PLearn::EntropyContrast::build (   )  [virtual]
 

simply calls inherited::build() then build_()

Reimplemented from PLearn::PLearner.

Definition at line 539 of file EntropyContrast.cc.

References build_().

void PLearn::EntropyContrast::build_ (   )  [private]
 

This does the actual building.

Reimplemented from PLearn::PLearner.

Definition at line 459 of file EntropyContrast.cc.

References bias_hidden, bias_output, df_dx, f_x, f_x_hat, full_sum, g_x, grad_C_extra_cost_wrt_f_x, grad_C_generated_wrt_f_x_hat, grad_C_real_wrt_f_x, grad_C_wrt_df_dx, grad_extra_wrt_v, grad_extra_wrt_w, grad_H_f_x_hat_wrt_bias_hidden, grad_H_f_x_hat_wrt_bias_output, grad_H_f_x_hat_wrt_v, grad_H_f_x_hat_wrt_w, grad_H_f_x_wrt_bias_hidden, grad_H_f_x_wrt_bias_output, grad_H_f_x_wrt_v, grad_H_f_x_wrt_w, grad_H_g_wrt_w, inputsize, PLearn::PP< VMatrix >::isNull(), learning_rate, PLearn::VMat::length(), mu_f, mu_f_hat, mu_f_square, mu_g, n, n_seen_examples, nconstraints, nhidden, PLearn::TMat< T >::resize(), PLearn::TVec< T >::resize(), sigma_f, sigma_f_hat, sigma_f_square, sigma_g, starting_learning_rate, v, w, PLearn::VMat::width(), x, x_hat, z_x, and z_x_hat.

Referenced by build().

void PLearn::EntropyContrast::compute_df_dx (  Mat &  df_dx,
const Vec &  input
)  [private]
 

Compute df/dx, given x(input).

Definition at line 254 of file EntropyContrast.cc.

References bias_hidden, PLearn::diag(), PLearn::diagonalizedFactorsProduct(), PLearn::TVec< T >::fill(), nhidden, PLearn::product(), PLearn::square(), PLearn::tanh(), v, and w.

Referenced by train().

void PLearn::EntropyContrast::compute_diversity_cost (  const Vec &  f_x,
const Vec &  cost,
Vec &  grad_C_extra_cost_wrt_f_x
)  [private]
 

Compute the cost and the gradiant for the diversity cost given by C_i = sum_j<i {cov((f_i)^2,(f_j)^2)}.

Definition at line 229 of file EntropyContrast.cc.

References PLearn::TVec< T >::fill(), full_sum, PLearn::VMat::length(), mu_f, nconstraints, PLearn::pow(), and sigma_f.

Referenced by train().

void PLearn::EntropyContrast::compute_extra_grad_wrt_df_dx (  Mat &  grad_C_wrt_df_dx  )  [private]
 

compute the grad extra_cost wrt df_dx

Definition at line 375 of file EntropyContrast.cc.

References df_dx, PLearn::dot(), k, n, and nconstraints.

Referenced by train().

void PLearn::EntropyContrast::computeCostsFromOutputs (  const Vec &  input,
const Vec &  output,
const Vec &  target,
Vec &  costs
)  const [virtual]
 

Computes the costs from already computed output.

The only computed cost is the squared_reconstruction_error

Implements PLearn::PLearner.

Definition at line 786 of file EntropyContrast.cc.

void PLearn::EntropyContrast::computeNNcontinuous_constraints (  Vec &  hidden_units,
Vec &  output_units
)  [private]
 

Compute the output units given the hidden units.

Definition at line 166 of file EntropyContrast.cc.

References bias_output, nconstraints, nhidden, and w.

Referenced by get_NNcontinuous_output().

void PLearn::EntropyContrast::computeNNcontinuous_hidden (  const Vec &  input_units,
Vec &  hidden_units
)  [private]
 

compute the hidden units of the NNet given the input

Definition at line 149 of file EntropyContrast.cc.

References bias_hidden, PLearn::compute_tanh(), n, nhidden, and v.

Referenced by get_NNcontinuous_output().

void PLearn::EntropyContrast::computeOutput (  const Vec &  input,
Vec &  output
)  const [virtual]
 

Computes the output from the input.

Implements PLearn::PLearner.

Definition at line 777 of file EntropyContrast.cc.

void PLearn::EntropyContrast::declareOptions (  OptionList &  ol  )  [static, protected]
 

Declares this class' options.

Reimplemented from PLearn::PLearner.

Definition at line 69 of file EntropyContrast.cc.

References PLearn::declareOption(), and PLearn::OptionList.

void PLearn::EntropyContrast::forget (   )  [virtual]
 

(Re-)initializes the PLearner in its fresh state (that state may depend on the 'seed' option) And sets 'stage' back to 0 (this is the stage of a fresh learner!)

Implements PLearn::PLearner.

Definition at line 559 of file EntropyContrast.cc.

References initialize_NNcontinuous().

Referenced by train().

void PLearn::EntropyContrast::gen_normal_0_1 (  Vec &  output  )  [private]
 

Fill a vector with numbers from a gaussian having mu=0 , and sigma=1 This can be used for the generataion of the data.

Definition at line 193 of file EntropyContrast.cc.

References PLearn::gaussian_01(), and PLearn::TVec< T >::length().

Referenced by train().

void PLearn::EntropyContrast::get_gen_grad_variance_wrt_f (  const Vec &  f_x_hat,
Vec &  grad
)  [private]
 

Compute d Var(f_x_hat) / df_x_hat.

Definition at line 280 of file EntropyContrast.cc.

References PLearn::TVec< T >::length(), mu_f_hat, and sigma_f_hat.

Referenced by train().

void PLearn::EntropyContrast::get_NNcontinuous_output (  const Vec &  input_units,
Vec &  output_units,
Vec &  hidden_units
)  [private]
 

Compute the output units and also the hidden units given the input.

Definition at line 180 of file EntropyContrast.cc.

References computeNNcontinuous_constraints(), and computeNNcontinuous_hidden().

Referenced by train().

void PLearn::EntropyContrast::get_real_grad_variance_wrt_f (  const Vec &  f_x,
Vec &  grad
)  [private]
 

Compute d Var(f_x) / df_x.

Definition at line 269 of file EntropyContrast.cc.

References PLearn::TVec< T >::length(), mu_f, and sigma_f.

Referenced by train().

string PLearn::EntropyContrast::getInfo (   )  [inline, private]
 

Definition at line 181 of file EntropyContrast.h.

References PLearn::split().

Referenced by train().

TVec< string > PLearn::EntropyContrast::getTestCostNames (   )  const [virtual]
 

Returns [ "squared_reconstruction_error" ].

Implements PLearn::PLearner.

Definition at line 791 of file EntropyContrast.cc.

TVec< string > PLearn::EntropyContrast::getTrainCostNames (   )  const [virtual]
 

No trian costs are computed for this learner.

Implements PLearn::PLearner.

Definition at line 796 of file EntropyContrast.cc.

void PLearn::EntropyContrast::initialize_NNcontinuous (   )  [private]
 

Initialize all the data structures for the NNet.

Definition at line 119 of file EntropyContrast.cc.

References bias_hidden, bias_output, PLearn::TVec< T >::fill(), PLearn::fill_random_uniform(), full, mu_f, mu_f_hat, mu_f_square, mu_g, sigma_f, sigma_f_hat, sigma_f_square, sigma_g, v, and w.

Referenced by forget().

void PLearn::EntropyContrast::makeDeepCopyFromShallowCopy (  map< const void *, void * > &  copies  )  [virtual]
 

Transforms a shallow copy into a deep copy.

Definition at line 546 of file EntropyContrast.cc.

int PLearn::EntropyContrast::outputsize (   )  const [virtual]
 

returns the size of this learner's output, (which typically may depend on its inputsize(), targetsize() and set options)

Implements PLearn::PLearner.

Definition at line 554 of file EntropyContrast.cc.

References nconstraints.

PLearn::EntropyContrast::PLEARN_DECLARE_OBJECT (  EntropyContrast   ) 
 

void PLearn::EntropyContrast::reconstruct (  const Vec &  output,
Vec &  input
)  const
 

Reconstructs an input from a (possibly partial) output (i.e. the first few princial components kept).

Definition at line 782 of file EntropyContrast.cc.

void PLearn::EntropyContrast::set_NNcontinuous_gradient (  Vec &  grad_C_real_wrt_f_x,
Mat &  grad_H_f_x_wrt_w,
Mat &  grad_H_f_x_wrt_v,
Vec &  hidden_units,
Vec &  input_units,
Vec &  grad_H_f_x_wrt_bias_hidden,
Vec &  grad_H_f_x_wrt_bias_output
)  [private]
 

Compute all the gradiants wrt to the parameters of the neural network.

Definition at line 291 of file EntropyContrast.cc.

References bias_hidden, k, n, nconstraints, nhidden, PLearn::sum(), PLearn::tanh(), v, and w.

Referenced by train().

void PLearn::EntropyContrast::set_NNcontinuous_gradient_from_extra_cost (  Mat &  grad_C_wrt_df_dx,
const Vec &  input
)  [private]
 

do the bprop step for NNet, compute all the gradiants

Definition at line 402 of file EntropyContrast.cc.

References PLearn::addToDiagonal(), bias_hidden, PLearn::diag(), PLearn::TMat< T >::fill(), PLearn::TVec< T >::fill(), grad_extra_wrt_bias_hidden, grad_extra_wrt_v, grad_extra_wrt_w, n, nconstraints, nhidden, PLearn::product(), PLearn::productTranspose(), PLearn::square(), PLearn::tanh(), PLearn::transpose(), v, and w.

Referenced by train().

void PLearn::EntropyContrast::train (   )  [virtual]
 

The role of the train method is to bring the learner up to stage==nstages, updating the train_stats collector with training costs measured on-line in the process.

Implements PLearn::PLearner.

Definition at line 567 of file EntropyContrast.cc.

References alpha, compute_df_dx(), compute_diversity_cost(), compute_extra_grad_wrt_df_dx(), cost_extra, cost_gen, cost_real, decay_factor, df_dx, PLearn::diag(), PLearn::diagonalizedFactorsProduct(), PLearn::endl(), evaluate_every_n_epochs, evaluate_first_epoch, evaluation_method, f_x, f_x_hat, PLearn::TVec< T >::fill(), forget(), full, g_x, gen_method, gen_normal_0_1(), get_gen_grad_variance_wrt_f(), get_NNcontinuous_output(), get_real_grad_variance_wrt_f(), getInfo(), grad_C_extra_cost_wrt_f_x, grad_C_generated_wrt_f_x_hat, grad_C_real_wrt_f_x, grad_C_wrt_df_dx, grad_H_f_x_hat_wrt_bias_hidden, grad_H_f_x_hat_wrt_bias_output, grad_H_f_x_hat_wrt_v, grad_H_f_x_hat_wrt_w, grad_H_f_x_wrt_bias_hidden, grad_H_f_x_wrt_bias_output, grad_H_f_x_wrt_v, grad_H_f_x_wrt_w, k, learning_rate, PLearn::TVec< T >::length(), PLearn::VMat::length(), PLearn::manual_seed(), mu_f, mu_f_hat, mu_f_square, n_seen_examples, nhidden, PLearn::product(), set_NNcontinuous_gradient(), set_NNcontinuous_gradient_from_extra_cost(), sigma_f, sigma_f_hat, sigma_f_square, PLearn::sqrt(), PLearn::square(), starting_learning_rate, PLearn::tanh(), update_alpha(), update_mu_sigma_f(), update_NNcontinuous(), update_NNcontinuous_from_extra_cost(), v, w, weight_extra, weight_gen, weight_real, x, x_hat, z_x, and z_x_hat.

void PLearn::EntropyContrast::update_alpha (  int  stage,
int  current_input_index
)  [private]
 

Update the weight of a sample(alpha).

It can range from 1/2, when the first sample is presented, to 1/inputsize if stage > 0

Definition at line 217 of file EntropyContrast.cc.

References alpha, and inputsize.

Referenced by train().

void PLearn::EntropyContrast::update_mu_sigma_f (  const Vec &  f_x,
Vec &  mu,
Vec &  sigma
)  [private]
 

Given the output of the NNet it updates the running averages(mu, variance).

Definition at line 204 of file EntropyContrast.cc.

References alpha, and PLearn::square().

Referenced by train().

void PLearn::EntropyContrast::update_NNcontinuous (   )  [private]
 

update the parameters of the NNet from the regular cost

Definition at line 355 of file EntropyContrast.cc.

References bias_hidden, bias_output, grad_H_f_x_hat_wrt_bias_hidden, grad_H_f_x_hat_wrt_bias_output, grad_H_f_x_hat_wrt_v, grad_H_f_x_hat_wrt_w, grad_H_f_x_wrt_bias_hidden, grad_H_f_x_wrt_bias_output, grad_H_f_x_wrt_v, grad_H_f_x_wrt_w, learning_rate, n, nconstraints, nhidden, v, w, weight_decay_hidden, and weight_decay_output.

Referenced by train().

void PLearn::EntropyContrast::update_NNcontinuous_from_extra_cost (   )  [private]
 

update the parameters of the NNet from the extra cost given by the derivative(angle) cost

Definition at line 331 of file EntropyContrast.cc.

References bias_hidden, grad_extra_wrt_bias_hidden, grad_extra_wrt_v, grad_extra_wrt_w, learning_rate, n, nconstraints, nhidden, v, and w.

Referenced by train().

Member Data Documentation

real PLearn::EntropyContrast::alpha [private]
 

Definition at line 89 of file EntropyContrast.h.

Referenced by EntropyContrast(), train(), update_alpha(), and update_mu_sigma_f().

Vec PLearn::EntropyContrast::bias_hidden [private]
 

Definition at line 119 of file EntropyContrast.h.

Referenced by build_(), compute_df_dx(), computeNNcontinuous_hidden(), initialize_NNcontinuous(), set_NNcontinuous_gradient(), set_NNcontinuous_gradient_from_extra_cost(), update_NNcontinuous(), and update_NNcontinuous_from_extra_cost().

Vec PLearn::EntropyContrast::bias_output [private]
 

Definition at line 125 of file EntropyContrast.h.

Referenced by build_(), computeNNcontinuous_constraints(), initialize_NNcontinuous(), and update_NNcontinuous().

string PLearn::EntropyContrast::cost_extra
 

Definition at line 149 of file EntropyContrast.h.

Referenced by train().

string PLearn::EntropyContrast::cost_gen
 

Definition at line 148 of file EntropyContrast.h.

Referenced by train().

string PLearn::EntropyContrast::cost_real
 

Definition at line 147 of file EntropyContrast.h.

Referenced by train().

real PLearn::EntropyContrast::decay_factor
 

the learning rate

Definition at line 158 of file EntropyContrast.h.

Referenced by EntropyContrast(), and train().

Mat PLearn::EntropyContrast::df_dx [private]
 

Definition at line 132 of file EntropyContrast.h.

Referenced by build_(), compute_extra_grad_wrt_df_dx(), and train().

int PLearn::EntropyContrast::evaluate_every_n_epochs [private]
 

Definition at line 67 of file EntropyContrast.h.

Referenced by EntropyContrast(), and train().

bool PLearn::EntropyContrast::evaluate_first_epoch [private]
 

Definition at line 68 of file EntropyContrast.h.

Referenced by EntropyContrast(), and train().

string PLearn::EntropyContrast::evaluation_method
 

Definition at line 151 of file EntropyContrast.h.

Referenced by EntropyContrast(), and train().

Vec PLearn::EntropyContrast::f_x [private]
 

Definition at line 75 of file EntropyContrast.h.

Referenced by build_(), and train().

Vec PLearn::EntropyContrast::f_x_hat [private]
 

Definition at line 81 of file EntropyContrast.h.

Referenced by build_(), and train().

real PLearn::EntropyContrast::full [private]
 

Definition at line 129 of file EntropyContrast.h.

Referenced by initialize_NNcontinuous(), and train().

Vec PLearn::EntropyContrast::full_sum [private]
 

Definition at line 127 of file EntropyContrast.h.

Referenced by build_(), and compute_diversity_cost().

Vec PLearn::EntropyContrast::g_x [private]
 

Definition at line 117 of file EntropyContrast.h.

Referenced by build_(), and train().

string PLearn::EntropyContrast::gen_method
 

Definition at line 150 of file EntropyContrast.h.

Referenced by train().

Vec PLearn::EntropyContrast::grad_C_extra_cost_wrt_f_x [private]
 

Definition at line 78 of file EntropyContrast.h.

Referenced by build_(), and train().

Vec PLearn::EntropyContrast::grad_C_generated_wrt_f_x_hat [private]
 

Definition at line 82 of file EntropyContrast.h.

Referenced by build_(), and train().

Vec PLearn::EntropyContrast::grad_C_real_wrt_f_x [private]
 

Definition at line 76 of file EntropyContrast.h.

Referenced by build_(), and train().

Mat PLearn::EntropyContrast::grad_C_wrt_df_dx [private]
 

Definition at line 133 of file EntropyContrast.h.

Referenced by build_(), and train().

Vec PLearn::EntropyContrast::grad_extra_wrt_bias_hidden [private]
 

Definition at line 135 of file EntropyContrast.h.

Referenced by set_NNcontinuous_gradient_from_extra_cost(), and update_NNcontinuous_from_extra_cost().

Vec PLearn::EntropyContrast::grad_extra_wrt_bias_output [private]
 

Definition at line 135 of file EntropyContrast.h.

Mat PLearn::EntropyContrast::grad_extra_wrt_v [private]
 

Definition at line 134 of file EntropyContrast.h.

Referenced by build_(), set_NNcontinuous_gradient_from_extra_cost(), and update_NNcontinuous_from_extra_cost().

Mat PLearn::EntropyContrast::grad_extra_wrt_w [private]
 

Definition at line 134 of file EntropyContrast.h.

Referenced by build_(), set_NNcontinuous_gradient_from_extra_cost(), and update_NNcontinuous_from_extra_cost().

Vec PLearn::EntropyContrast::grad_H_f_x_hat_wrt_bias_hidden [private]
 

Definition at line 111 of file EntropyContrast.h.

Referenced by build_(), train(), and update_NNcontinuous().

Vec PLearn::EntropyContrast::grad_H_f_x_hat_wrt_bias_output [private]
 

Definition at line 110 of file EntropyContrast.h.

Referenced by build_(), train(), and update_NNcontinuous().

Mat PLearn::EntropyContrast::grad_H_f_x_hat_wrt_v [private]
 

Definition at line 105 of file EntropyContrast.h.

Referenced by build_(), train(), and update_NNcontinuous().

Mat PLearn::EntropyContrast::grad_H_f_x_hat_wrt_w [private]
 

Definition at line 103 of file EntropyContrast.h.

Referenced by build_(), train(), and update_NNcontinuous().

Vec PLearn::EntropyContrast::grad_H_f_x_wrt_bias_hidden [private]
 

Definition at line 108 of file EntropyContrast.h.

Referenced by build_(), train(), and update_NNcontinuous().

Vec PLearn::EntropyContrast::grad_H_f_x_wrt_bias_output [private]
 

Definition at line 107 of file EntropyContrast.h.

Referenced by build_(), train(), and update_NNcontinuous().

Mat PLearn::EntropyContrast::grad_H_f_x_wrt_v [private]
 

Definition at line 104 of file EntropyContrast.h.

Referenced by build_(), train(), and update_NNcontinuous().

Mat PLearn::EntropyContrast::grad_H_f_x_wrt_w [private]
 

Definition at line 102 of file EntropyContrast.h.

Referenced by build_(), train(), and update_NNcontinuous().

Mat PLearn::EntropyContrast::grad_H_g_wrt_w [private]
 

Definition at line 113 of file EntropyContrast.h.

Referenced by build_().

int PLearn::EntropyContrast::inputsize
 

The number of constraints.

Definition at line 155 of file EntropyContrast.h.

Referenced by build_(), and update_alpha().

real PLearn::EntropyContrast::learning_rate
 

Definition at line 157 of file EntropyContrast.h.

Referenced by build_(), EntropyContrast(), train(), update_NNcontinuous(), and update_NNcontinuous_from_extra_cost().

Vec PLearn::EntropyContrast::mu_f [private]
 

the number of hidden units, in the one existing hidden layer

Definition at line 94 of file EntropyContrast.h.

Referenced by build_(), compute_diversity_cost(), get_real_grad_variance_wrt_f(), initialize_NNcontinuous(), and train().

Vec PLearn::EntropyContrast::mu_f_hat [private]
 

Definition at line 97 of file EntropyContrast.h.

Referenced by build_(), get_gen_grad_variance_wrt_f(), initialize_NNcontinuous(), and train().

Vec PLearn::EntropyContrast::mu_f_square [private]
 

Definition at line 100 of file EntropyContrast.h.

Referenced by build_(), initialize_NNcontinuous(), and train().

Vec PLearn::EntropyContrast::mu_g [private]
 

Definition at line 116 of file EntropyContrast.h.

Referenced by build_(), and initialize_NNcontinuous().

int PLearn::EntropyContrast::n [private]
 

Definition at line 66 of file EntropyContrast.h.

Referenced by build_(), compute_extra_grad_wrt_df_dx(), computeNNcontinuous_hidden(), EntropyContrast(), set_NNcontinuous_gradient(), set_NNcontinuous_gradient_from_extra_cost(), update_NNcontinuous(), and update_NNcontinuous_from_extra_cost().

int PLearn::EntropyContrast::n_seen_examples
 

Definition at line 162 of file EntropyContrast.h.

Referenced by build_(), and train().

int PLearn::EntropyContrast::nconstraints
 

Definition at line 153 of file EntropyContrast.h.

Referenced by build_(), compute_diversity_cost(), compute_extra_grad_wrt_df_dx(), computeNNcontinuous_constraints(), EntropyContrast(), outputsize(), set_NNcontinuous_gradient(), set_NNcontinuous_gradient_from_extra_cost(), update_NNcontinuous(), and update_NNcontinuous_from_extra_cost().

int PLearn::EntropyContrast::nhidden [private]
 

Definition at line 92 of file EntropyContrast.h.

Referenced by build_(), compute_df_dx(), computeNNcontinuous_constraints(), computeNNcontinuous_hidden(), EntropyContrast(), set_NNcontinuous_gradient(), set_NNcontinuous_gradient_from_extra_cost(), train(), update_NNcontinuous(), and update_NNcontinuous_from_extra_cost().

Vec PLearn::EntropyContrast::sigma_f [private]
 

Definition at line 95 of file EntropyContrast.h.

Referenced by build_(), compute_diversity_cost(), get_real_grad_variance_wrt_f(), initialize_NNcontinuous(), and train().

Vec PLearn::EntropyContrast::sigma_f_hat [private]
 

Definition at line 98 of file EntropyContrast.h.

Referenced by build_(), get_gen_grad_variance_wrt_f(), initialize_NNcontinuous(), and train().

Vec PLearn::EntropyContrast::sigma_f_square [private]
 

Definition at line 101 of file EntropyContrast.h.

Referenced by build_(), initialize_NNcontinuous(), and train().

Vec PLearn::EntropyContrast::sigma_g [private]
 

Definition at line 115 of file EntropyContrast.h.

Referenced by build_(), and initialize_NNcontinuous().

real PLearn::EntropyContrast::starting_learning_rate
 

Definition at line 163 of file EntropyContrast.h.

Referenced by build_(), and train().

VMat PLearn::EntropyContrast::test_set [private]
 

Definition at line 84 of file EntropyContrast.h.

Mat PLearn::EntropyContrast::v [private]
 

Definition at line 71 of file EntropyContrast.h.

Referenced by build_(), compute_df_dx(), computeNNcontinuous_hidden(), initialize_NNcontinuous(), set_NNcontinuous_gradient(), set_NNcontinuous_gradient_from_extra_cost(), train(), update_NNcontinuous(), and update_NNcontinuous_from_extra_cost().

VMat PLearn::EntropyContrast::validation_set [private]
 

Reimplemented from PLearn::PLearner.

Definition at line 85 of file EntropyContrast.h.

Mat PLearn::EntropyContrast::w [private]
 

Definition at line 70 of file EntropyContrast.h.

Referenced by build_(), compute_df_dx(), computeNNcontinuous_constraints(), initialize_NNcontinuous(), set_NNcontinuous_gradient(), set_NNcontinuous_gradient_from_extra_cost(), train(), update_NNcontinuous(), and update_NNcontinuous_from_extra_cost().

real PLearn::EntropyContrast::weight_decay_hidden
 

Definition at line 161 of file EntropyContrast.h.

Referenced by update_NNcontinuous().

real PLearn::EntropyContrast::weight_decay_output
 

Definition at line 160 of file EntropyContrast.h.

Referenced by update_NNcontinuous().

real PLearn::EntropyContrast::weight_extra
 

the decay factor of the learning rate

Definition at line 159 of file EntropyContrast.h.

Referenced by EntropyContrast(), and train().

real PLearn::EntropyContrast::weight_gen
 

the decay factor of the learning rate

Definition at line 159 of file EntropyContrast.h.

Referenced by EntropyContrast(), and train().

real PLearn::EntropyContrast::weight_real
 

the decay factor of the learning rate

Definition at line 159 of file EntropyContrast.h.

Referenced by EntropyContrast(), and train().

Vec PLearn::EntropyContrast::x [private]
 

Definition at line 74 of file EntropyContrast.h.

Referenced by build_(), and train().

Vec PLearn::EntropyContrast::x_hat [private]
 

Definition at line 80 of file EntropyContrast.h.

Referenced by build_(), and train().

Vec PLearn::EntropyContrast::z_x [private]
 

Definition at line 120 of file EntropyContrast.h.

Referenced by build_(), and train().

Vec PLearn::EntropyContrast::z_x_hat [private]
 

Definition at line 122 of file EntropyContrast.h.

Referenced by build_(), and train().

The documentation for this class was generated from the following files:
Generated on Tue Aug 17 16:27:52 2004 for PLearn by doxygen 1.3.7