Class List

Here are the classes, structs, unions and interfaces with brief descriptions:

[detail level 123]

▼NOpenNN | |

CAdaptiveMomentEstimation | This concrete class represents the adaptive moment estimation(Adam) training algorithm, based on adaptative estimates of lower-order moments |

CBoundingLayer | This class represents a layer of bounding neurons |

CBoxPlot | BoxPlot is a visual aid to study the distributions of dataset variables |

CConjugateGradient | This concrete class represents a conjugate gradient training algorithm, based on solving sparse systems |

CConvolutionalLayer | |

CCorrelationResults | This structure provides the results obtained from the correlations |

CCrossEntropyError | This class represents the cross entropy error term, used for predicting probabilities |

▼CDataSet | This class represents the concept of data set for data modelling problems, such as function regression, classification, time series prediction, images approximation and images classification |

CColumn | This structure represents the columns of the DataSet |

CDescriptives | This structure contains the simplest Descriptives for a set, variable, etc. It includes : |

▼CGeneticAlgorithm | This concrete class represents a genetic algorithm, inspired by the process of natural selection[1] such as mutation, crossover and selection |

CGeneticAlgorithmResults | This structure contains the training results for the genetic algorithm method. |

CGradientDescent | This concrete class represents the gradient descent optimization algorithm[1], used to minimize loss function |

▼CGrowingInputs | This concrete class represents a growing inputs algorithm for the InputsSelection as part of the ModelSelection[1] class |

CGrowingInputsResults | This structure contains the training results for the growing inputs method |

CHistogram | The Histograms is a visual aid to study the distributions of dataset variables |

▼CIncrementalNeurons | This concrete class represents an incremental algorithm for the NeuronsSelection as part of the ModelSelection[1] class |

CIncrementalNeuronsResults | This structure contains the training results for the incremental order method |

▼CInputsSelection | This abstract class represents the concept of inputs selection algorithm for a ModelSelection[1] |

CResults | This structure contains the results from the inputs selection |

▼CKMeans | |

CResults | |

▼CLayer | This abstract class represents the concept of layer of neurons in OpenNN |

CFirstOrderActivations | |

▼CLearningRateAlgorithm | This class is used by many different optimization algorithms to calculate the training rate given a training direction |

CTriplet | Defines a set of three points(A, U, B) for bracketing a directional minimum |

CLevenbergMarquardtAlgorithm | This concrete class represents a Levenberg-Marquardt Algorithm training algorithm[1] for the sum squared error loss index for a neural network |

CLongShortTermMemoryLayer | |

▼CLossIndex | This abstrac class represents the concept of loss index composed of an error term and a regularization term |

CFirstOrderLoss | A loss index composed of several terms, this structure represent the First Order for this function |

CSecondOrderLoss | This structure represents the Second Order in the loss function |

CMatrix | This template class defines a matrix for general purpose use |

CMeanSquaredError | This class represents the mean squared error term |

CMinkowskiError | This class represents the Minkowski error term |

▼CModelSelection | This class represents the concept of model selection[1] algorithm in OpenNN |

CResults | This structure contains the results from the model selection process |

CNeuralNetwork | This class represents the concept of neural network in the OpenNN library |

▼CNeuronsSelection | This abstract class represents the concept of neurons selection algorithm for a ModelSelection[1] |

CResults | This structure contains the results from the order selection |

CNormalizedSquaredError | This class represents the normalized squared error term |

CNumericalDifferentiation | This class contains methods for numerical differentiation of functions |

▼COptimizationAlgorithm | This abstract class represents the concept of optimization algorithm for a neural network in OpenNN library |

CResults | This structure contains the optimization algorithm results. |

CPerceptronLayer | This class represents a layer of perceptrons |

CPoolingLayer | This class is used to store information about the Pooling Layer in Convolutional Neural Network(CNN) |

CPrincipalComponentsLayer | This class represents the layer of principal component analysis |

CProbabilisticLayer | This class represents a layer of probabilistic neurons |

▼CPruningInputs | This concrete class represents a pruning inputs algorithm for the InputsSelection as part of the ModelSelection[1] class |

CPruningInputsResults | |

CQuasiNewtonMethod | This concrete class represents a quasi-Newton training algorithm[1], used to minimize loss function |

CRecurrentLayer | |

CRegressionResults | This structure provides the results obtained from the regression analysis |

▼CResponseOptimization | This class is used to optimize model response identify the combinations of variable settings jointly optimize a set of responses |

CResults | |

CScalingLayer | This class represents a layer of scaling neurons |

CStochasticGradientDescent | This concrete class represents the stochastic gradient descent optimization algorithm[1] for a loss index of a neural network |

CSumSquaredError | This class represents the sum squared peformance term functional |

CTensor | This template class defines a tensor for general purpose use |

▼CTestingAnalysis | This class contains tools for testing neural networks in different learning tasks |

CBinaryClassifcationRates | Structure with the binary classification rates |

CKolmogorovSmirnovResults | Structure with the results from Kolmogorov-Smirnov analysis |

CLinearRegressionAnalysis | Structure with the results from a linear regression analysis |

CRocAnalysisResults | Structure with the results from a roc curve analysis |

CTrainingStrategy | This class represents the concept of training strategy for a neural network in OpenNN |

CUnscalingLayer | This class represents a layer of unscaling neurons |

CVector | This template represents an array of any kind of numbers or objects |

CWeightedSquaredError | This class represents the weighted squared error term |

▼Ntinyxml2 | |

CDynArray | |

CMemPool | |

▼CMemPoolT | |

CBlock | |

CItem | |

CStrPair | |

CXMLAttribute | |

CXMLComment | |

CXMLConstHandle | |

CXMLDeclaration | |

CXMLDocument | |

CXMLElement | |

CXMLHandle | |

CXMLNode | |

CXMLPrinter | |

CXMLText | |

CXMLUnknown | |

CXMLUtil | |

CXMLVisitor | |

CUnitTesting |