Uses of Interface
deepnetts.data.MLDataItem
Packages that use MLDataItem
Package
Description
Support for automatically building deep learning models using hyper-parameter search.
Data structures to store example data used for building machine learning models.
Data normalization methods, used to scale data to specific range, in order to make them suitable for use by a neural network.
Evaluation procedures for machine learning models, used to estimate how good models are performing when given new data that (that was not used for training).
Neural network architectures with their corresponding builders.
Commonly used loss functions, which are used to calculate error during the training as a difference between predicted and target output.
Training algorithms and related utilities.
- 
Uses of MLDataItem in deepnetts.automlMethods in deepnetts.automl that return types with arguments of type MLDataItemModifier and TypeMethodDescriptionfinal javax.visrec.ml.eval.Evaluator<NeuralNetwork, javax.visrec.ml.data.DataSet<? extends MLDataItem>> HyperParameterSearch.getEvaluator()Method parameters in deepnetts.automl with type arguments of type MLDataItemModifier and TypeMethodDescriptionHyperParameterSearch.evaluator(javax.visrec.ml.eval.Evaluator<NeuralNetwork, javax.visrec.ml.data.DataSet<? extends MLDataItem>> evaluator) 
- 
Uses of MLDataItem in deepnetts.dataClasses in deepnetts.data with type parameters of type MLDataItemModifier and TypeClassDescriptionclassTabularDataSet<T extends MLDataItem>Basic data set with tabular data.Classes in deepnetts.data that implement MLDataItemModifier and TypeClassDescriptionclassExample image to train a deep learning model.static classRepresents a basic data set item (single row) with input tensor and target vector in a data set.Methods in deepnetts.data that return types with arguments of type MLDataItemModifier and TypeMethodDescriptionjavax.visrec.ml.data.DataSet<MLDataItem> TrainTestSplit.getTestSet()javax.visrec.ml.data.DataSet<MLDataItem> TrainTestSplit.getTrainingSet()Constructor parameters in deepnetts.data with type arguments of type MLDataItemModifierConstructorDescriptionTrainTestSplit(javax.visrec.ml.data.DataSet<MLDataItem> trainingSet, javax.visrec.ml.data.DataSet<MLDataItem> testSet) 
- 
Uses of MLDataItem in deepnetts.data.normMethod parameters in deepnetts.data.norm with type arguments of type MLDataItemModifier and TypeMethodDescriptionvoidDecimalScaler.apply(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) Performs normalization on the given inputs.voidMaxScaler.apply(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) Performs normalization on the given inputs.voidMinMaxScaler.apply(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) Performs normalization on the given inputs.voidRangeScaler.apply(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) Performs normalization on the given inputs.voidStandardizer.apply(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) Constructor parameters in deepnetts.data.norm with type arguments of type MLDataItemModifierConstructorDescriptionDecimalScaler(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) Creates a new instance of max normalizer initialized to max values in given data set.MaxScaler(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) Creates a new instance of max normalizer initialized to max values in given data set.MinMaxScaler(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) Creates a new instance of max normalizer initialized to max values in given data set.Standardizer(javax.visrec.ml.data.DataSet<MLDataItem> dataSet) 
- 
Uses of MLDataItem in deepnetts.evalMethod parameters in deepnetts.eval with type arguments of type MLDataItemModifier and TypeMethodDescriptionClassifierEvaluator.evaluate(NeuralNetwork neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet) Performs classifier evaluation and returns classification performance metrics.javax.visrec.ml.eval.EvaluationMetricsRegresionEvaluator.evaluate(NeuralNetwork neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet) static ClassificationMetricsEvaluators.evaluateClassifier(NeuralNetwork<?> neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet) static RegressionMetricsEvaluators.evaluateRegressor(NeuralNetwork<?> neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet) Evaluates specified neural network with test set, as a regression model and returns basic regression evauation metrics.
- 
Uses of MLDataItem in deepnetts.netMethod parameters in deepnetts.net with type arguments of type MLDataItemModifier and TypeMethodDescriptionjavax.visrec.ml.eval.EvaluationMetricsNeuralNetwork.test(javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet) Tests how good are predictions of this network using specified test set.voidNeuralNetwork.train(javax.visrec.ml.data.DataSet<? extends MLDataItem> trainingSet) Trains the neural network using specified training set.
- 
Uses of MLDataItem in deepnetts.net.lossMethod parameters in deepnetts.net.loss with type arguments of type MLDataItemModifier and TypeMethodDescriptiondefault floatLossFunction.valueFor(NeuralNetwork nnet, javax.visrec.ml.data.DataSet<? extends MLDataItem> dataSet) Calculates and returns loss function value for the given neural network and data set.
- 
Uses of MLDataItem in deepnetts.net.trainMethod parameters in deepnetts.net.train with type arguments of type MLDataItemModifier and TypeMethodDescriptionKFoldCrossValidation.Builder.evaluator(javax.visrec.ml.eval.Evaluator<NeuralNetwork, javax.visrec.ml.data.DataSet<? extends MLDataItem>> evaluator) voidBackpropagationTrainer.setTestSet(javax.visrec.ml.data.DataSet<MLDataItem> testSet) Test set is used after the training to estimate performance of the trained model and generalization ability with new data.voidBackpropagationTrainer.train(javax.visrec.ml.data.DataSet<? extends MLDataItem> trainingSet) Runs training using specified training set.voidBackpropagationTrainer.train(javax.visrec.ml.data.DataSet<MLDataItem> trainingSet, javax.visrec.ml.data.DataSet<MLDataItem> validationSet) Runs training using given training and validation sets.voidTrainer.train(javax.visrec.ml.data.DataSet<? extends MLDataItem> trainingSet) Trains this model using specified training set.