File List

Here is a list of all files with brief descriptions:
AdpBP.h [code]Offers the two versions of the gradient descent based optimization algorithm with individual adaptive learning rates by Silva and Almeida (Adaptive BackPropagation)
ArtificialDistributions.cpp [code]Artificial benchmark data
ArtificialDistributions.h [code]Artificial benchmark data
BFGS.cpp [code]Offers the Broyden-Fletcher-Goldfarb-Shanno algorithm for the optimization of models
BFGS.h [code]Offers the Broyden-Fletcher-Goldfarb-Shanno algorithm for the optimization of models
BinaryCriterion.h [code]Uses thresholds for transforming output and target vectors into binary vectors and then calculates the classification error
CG.cpp [code]Offers the Conjugate Gradients algorithm for the optimization of models
CG.h [code]Offers the Conjugate Gradients algorithm for the optimization of models
ClassificationError.cpp [code]Compute the fraction of classification errors
ClassificationError.h [code]Compute the fraction of classification errors
CMAOptimizer.cpp [code]The CMA-ES as a ReClaM Optimizer
CMAOptimizer.h [code]The CMA-ES as a ReClaM Optimizer
ComponentWiseModel.cpp [code]The ComponentWiseModel encapsulates the component wise application of a base model
ComponentWiseModel.h [code]The ComponentWiseModel encapsulates the component wise application of a base model
ConcatenatedModel.cpp [code]The ConcatenatedModel encapsulates a chain of basic models
ConcatenatedModel.h [code]The ConcatenatedModel encapsulates a chain of basic models
CoverTree.cpp [code]
CoverTree.h [code]
createConnectionMatrix.h [code]Offers methods for creating connection matrices for neural networks
CrossEntropy.h [code]Error measure for classication tasks that can be used as the objective function for training
CrossEntropyIndependent.h [code]Error measure for classification tasks of non exclusive attributes that can be used for model training
CrossValidation.cpp [code]Cross Validation
CrossValidation.h [code]Cross Validation
Dataset.cpp [code]Functions for loading ReClaM datasets
Dataset.h [code]Functions for loading ReClaM datasets
DF_CrossEntropy.h [code]Error measure for classication tasks that can be used as the objective function for training
DF_CrossEntropyIndependent.h [code]Error measure for classification tasks of non exclusive attributes that can be used for model training
DF_MeanSquaredError.h [code]Mean Squared Error, using the GeneralDerivative interface
Documentation [code]
EarlyStopping.cpp [code]Used for monitoring purposes, to avoid overfitting
EarlyStopping.h [code]Used for monitoring purposes, to avoid overfitting
ErrorFunction.cpp [code]Base class of all error measures
ErrorFunction.h [code]Base class of all error measures
ErrorPercentage.h [code]Calculates the error percentage based on the mean squared error
FFNet.cpp [code]Offers the functions to create and to work with a feed-forward network
FFNet.h [code]Offers the functions to create and to work with a feed-forward network
FFNetSource.h [code]
GaussianProcess.cpp [code]Gaussian Process implementation
GaussianProcess.h [code]Gaussian Process header
GaussKernel.cpp [code]Gauss kernels with adaptive covariance matrices
GaussKernel.h [code]Gauss kernels with adaptive covariance matrices
GridSearch.cpp [code]Optimization by grid or point set search
GridSearch.h [code]Optimization by grid or point set search
InverseClassSeparability.cpp [code]Inverse of the Class Separability Measure J by Huilin Xiong and M. N. S. Swamy
InverseClassSeparability.h [code]Inverse of the Class Separability Measure J by Huilin Xiong and M. N. S. Swamy
JaakkolaHeuristic.cpp [code]Jaakkola's heuristic and related quantities for Gaussian kernel selection
JaakkolaHeuristic.h [code]Jaakkola's heuristic and related quantities for Gaussian kernel selection
KalmanFilter.cpp [code]Standard linear Kalman filter
KalmanFilter.h [code]Standard linear Kalman filter
KernelFunction.cpp [code]Kernel function base class and simple function implementations
KernelFunction.h [code]This file contains the definition of a kernel function as well as basic examples of kernel functions
KernelKMeans.cpp [code]Kernel k-means clustering
KernelKMeans.h [code]Kernel k-means clustering
KernelMeanClassifier.cpp [code]Kernel Mean Classifier
KernelMeanClassifier.h [code]Kernel Mean Classifier
KernelNearestNeighbor.cpp [code]Kernel k-Nearest Neighbor Classifier
KernelNearestNeighbor.h [code]Kernel k-Nearest Neighbor Classifier
KTA.cpp [code]Implementation of the (negative) Kernel Target Alignment (KTA) as proposed by Nello Cristianini
KTA.h [code]Implementation of the (negative) Kernel Target Alignment (KTA) as proposed by Nello Cristianini
LDA.cpp [code]Train a LinearClassifier using Linear Discriminant Analysis (LDA)
LDA.h [code]Linear Discriminant Analysis (LDA)
LinearEquation.cpp [code]Model and Error Function for the iterative approximate solution of a linear system
LinearEquation.h [code]Model and Error Function for the iterative approximate solution of a linear system
LinearModel.cpp [code]Linear models on a real vector space
LinearModel.h [code]Linear models on a real vector space
LinearRegression.cpp [code]Linear Regression
LinearRegression.h [code]Linear Regression
LinOutFFNet.h [code]Offers the functions to create and to work with (F)eed-(F)orward (Net)works with (Lin)ear (Out)put
LinOutMSEBFFNet.h [code]Offers the functions to create and to work with (F)eed-(F)orward (Net)works with (Lin)ear (Out)put
LMSEFFNet.h [code]Offers the functions to create and to work with a feed-forward network with explicit defined neuron-to-bias connections. The network is combined with the mean squared error measure. This combination is created due to computational efficiency
LOO.cpp [code]Leave One Out (LOO) Error for Support Vector Machines
LOO.h [code]Leave One Out (LOO) Error for Support Vector Machines
MeanSquaredError.h [code]Calculates the mean squared error
Model.cpp [code]Base class of all models
Model.h [code]Base class of all models
ModelInterface.h [code][DEPRECATED] Realizes the communication between the different modules
ModelWithErrorFunction.h [code]Abstarct base class for objects which are both models and error functions
MSEFFNet.cpp [code]Offers the functions to create and to work with a feed-forward network combined with the mean squared error measure. This combination is created due to computational efficiency
MSEFFNet.h [code]Offers the functions to create and to work with a feed-forward network combined with the mean squared error measure. This combination is created due to computational efficiency
MSERBFNet.h [code]Offers the functions to create and to work with radial basis function networks and to train it with the mean squared error. This combination provides more computational efficiency compared to using the class MeanSquaredError
MSERNNet.cpp [code]Mean Squared Error Recurrent Neural Network
MSERNNet.h [code]Offers the functions to create and to work with a recurrent neural network. The network is combined with the mean squared error measure. This combination is created due to computational efficiency
NegativeLogLikelihood.cpp [code]Negative logarithm of the likelihood of a probabilistic binary classification model
NegativeLogLikelihood.h [code]Negative logarithm of the likelihood of a probabilistic binary classification model
NegativePolarization.cpp [code]Implementation of the negative Kernel Polarization Measure, that is, Kernel Target Alignment without normalization
NegativePolarization.h [code]Implementation of the negative Kernel Polarization Measure, that is, Kernel Target Alignment without normalization
NetParams.cpp [code]Offers functions for easily reading information about a network, an error measure and an optimization algorithm from a configuration file
NetParams.h [code]Easily configuration file reading for neural networks
NoisyRprop.cpp [code]Rprop for noisy function evaluations
NoisyRprop.h [code]Rprop for noisy function evaluations
NoisySvmLikelihood.cpp [code]Model selection objective function for SVMs
NoisySvmLikelihood.h [code]Model selection objective function for SVMs
NormedModels.h [code]Wrapper models normalizing the output
Optimizer.cpp [code]Base class of all optimizers
Optimizer.h [code]Base class of all optimizers
Paraboloid.h [code]Convex quadratic model and error function
PCA.cpp [code]Train a (affine) linear map using Principal Component Analysis (PCA)
PCA.h [code]Principal Component Analysis (PCA)
Perceptron.cpp [code]Perceptron online learning algorith,
Perceptron.h [code]Perceptron online learning algorith
ProbenBNet.h [code]Offers a predefined feed-forward neural network
ProbenNet.h [code]Offers a predefined feed-forward neural network
QuadraticProgram.cpp [code]Quadratic programming for Support Vector Machines
QuadraticProgram.h [code]Quadratic programming for Support Vector Machines
Quickprop.h [code]This file includes the popular heuristic optimization method named "Quickprop"
RadiusMargin.cpp [code]Squared radius margin quotient
RadiusMargin.h [code]Squared radius margin quotient
RBFNet.h [code]Offers the functions to create and to work with radial basis function networks
ROC.cpp [code]Computes a "receiver operator characteristics" curve
ROC.h [code]Computes a "receiver operator characteristics" curve
Rprop.h [code]This file offers classes to use the Resilient-Backpropagation-algorithm for the optimization of the adaptive parameters of a network
SigmoidFit.cpp [code]Optimization of the SigmoidModel according to Platt, 1999
SigmoidFit.h [code]Optimization of the SigmoidModel according to Platt, 1999
SigmoidModel.cpp [code]Sigmoidal functions
SigmoidModel.h [code]Sigmoidal functions
SpanBound.cpp [code]Compute the SpanBound for the 2-norm SVM
SpanBound.h [code]SpanBound for the 2-norm SVM
SpanBound1.cpp [code]Compute the SpanBound for the 1-norm SVM
SpanBound1.h [code]SpanBound for the 1-norm SVM
SquaredError.h [code]Calculates the sum-of-squares error
SteepestDescent.h [code]The simplest learning strategy
StochasticGradientDescent.h [code]Learning strategies based on SteepestDescent, but with randomly chosen patterns
Svm.cpp [code]Support Vector Machine implementation
Svm.h [code]Support Vector Machine interface
SvmApproximation.cpp [code]Approximation of Support Vector Machines (SVMs)
SvmApproximation.h [code]Approximation of Support Vector Machines (SVMs)
TanhNet.h [code]Offers a predefined feed-forward neural network
ValidationError.cpp [code]Compute the error on a hold out set
ValidationError.h [code]Compute the error on a hold out set
Variance.h [code]Cariance of data in each column of a data set
VarianceEstimator.cpp [code]Offers the methods to deal with active learning of a neural network
VarianceEstimator.h [code]Offers the methods to deal with active learning of a neural network
WTA.h [code]Winner-takes-all error function