Accord.MachineLearning.Performance Namespace

Base class for GridSearchTModel, TInput, TOutput methods.

Base class for performance measurement methods based on splitting the data into multiple sets, such as SplitSetValidationTModel, TInput, TOutput, CrossValidationTModel, TInput, TOutput and BootstrapTModel, TInput, TOutput.

Base class for performance measurement methods based on splitting the data into multiple sets, such as SplitSetValidationTModel, TInput, TOutput, CrossValidationTModel, TInput, TOutput and BootstrapTModel, TInput, TOutput.

Bootstrap method for generalization performance measurements (with support for stratification and default loss function for classification).

Bootstrap method for generalization performance measurements.

Bootstrap validation analysis results.

k-Fold cross-validation (with support for stratification and default loss function for classification).

k-Fold cross-validation.

k-Fold cross-validation.

Class for representing results acquired through a k-fold cross-validation analysis.

Subset of a larger dataset.

Subset of a larger dataset.

Grid search procedure for automatic parameter tuning.

Grid search procedure for automatic parameter tuning.

Grid search procedure for automatic parameter tuning.

Grid search procedure for automatic parameter tuning.

Grid search procedure for automatic parameter tuning.

Range of parameters to be tested in a grid search.

Contains results from the grid-search procedure.

Contains results from the grid-search procedure.

Training and validation errors of a model.

Information class to store the training and validation errors of a model.

Split-Set Validation (with support for stratification and default loss function for classification).

Split-Set Validation.

Training-Validation-Testing data split.

Training-Test split.

Training-Validation-Testing data split.

Training-Validation split.

Training-Validation-Testing data split.

Training-Validation-Test split.

Common interfae for data splits.

Non-generic interface for GridSearchRangeT.

Function signature for a function that can compute a performance metric (i.e. a ILossT) from a set of expected (ground-truth) and actual (model prediction) output values. Additional information about the metric (such as its variance) or the learning problem (such as the expected number of classes) can be set in the object passed as the info parameter.

Function signature for a function that creates a machine learning model given a set of parameter values. This function should use the parameters to create and configure a ISupervisedLearningTModel, TInput, TOutput learning algorithm that can in turn be used to create a new machine learning model with those parameters.

Function signature for a function that creates a machine learning model from a DataSubsetTInput, TOutput subset of the training data. This function should take a subset of the data as input, and create a ISupervisedLearningTModel, TInput, TOutput algorithm that can create a model using this given subset.

Function signature for a function that specifies how a teacher should be used to create a new TModel.