Package org.deeplearning4j.eval

Interface Summary

Interface	Description
IEvaluation<T extends IEvaluation>	A general purpose interface for evaluating neural networks - methods are shared by implemetations such as Evaluation, RegressionEvaluation, ROC, ROCMultiClass

Class Summary

Class	Description
BaseEvaluation<T extends BaseEvaluation>	BaseEvaluation implement common evaluation functionality (for time series, etc) for Evaluation, RegressionEvaluation, ROC, ROCMultiClass etc.
ConfusionMatrix<T extends java.lang.Comparable<? super T>>
EvalTest	Created by agibsonccc on 12/22/14.
Evaluation	Evaluation metrics: precision, recall, f1
EvaluationBinary	EvaluationBinary: used for evaluating networks with binary classification outputs.
EvaluationBinaryTest	Created by Alex on 20/03/2017.
EvaluationToolsTests	Created by Alex on 07/01/2017.
EvaluationUtils	Utility methods for performing evaluation
RegressionEvalTest
RegressionEvaluation	Evaluation method for the evaluation of regression algorithms. Provides the following metrics, for each column: - MSE: mean squared error - MAE: mean absolute error - RMSE: root mean squared error - RSE: relative squared error - correlation coefficient See for example: http://www.saedsayad.com/model_evaluation_r.htm For classification, see Evaluation
ROC	ROC (Receiver Operating Characteristic) for binary classifiers, using the specified number of threshold steps.
ROC.CountsForThreshold
ROC.PrecisionRecallPoint
ROC.ROCValue
ROCBinary	ROC (Receiver Operating Characteristic) for multi-task binary classifiers, using the specified number of threshold steps.
ROCBinary.CountsForThreshold
ROCBinary.PrecisionRecallPoint
ROCBinary.ROCValue
ROCBinaryTest	Created by Alex on 21/03/2017.
ROCMultiClass	ROC (Receiver Operating Characteristic) for multi-class classifiers, using the specified number of threshold steps.
ROCTest	Created by Alex on 04/11/2016.