public void MeanSquareError_ThrowOnLengthMismatch() { var target = new[] { 1.0, 1.0 }; var output = new[] { 1.0 }; Assert.Throws <NeuralNetworkException>(() => ErrorCalculations.MeanSquareError(target, output)); }
public void CrossEntropyError_Calculate() { var target = new[] { 0.05, 0.8, 0.15 }; var output = new[] { 0.3, 0.5, 0.2 }; var actual = ErrorCalculations.CrossEntropyError(target, output); var expected = 0.856132071529368; Assert.Equal(expected, actual, 12); }
public void MeanSquareError_Calculate() { var target = new[] { 0.05, 0.8, 0.15 }; var output = new[] { 0.3, 0.5, 0.2 }; var actual = ErrorCalculations.MeanSquareError(target, output); var expected = 0.0516666666666667; Assert.Equal(expected, actual, 12); }
public ErrorsViewModel(Types.Signal original, Types.Signal processed, int neighboursCount, double samplingFrequency) { _neighboursCount = neighboursCount; _samplingFrequency = samplingFrequency; _meanSquaredError = ErrorCalculations.meanSquaredError(original.points, processed.points); _signalToNoiseRatio = ErrorCalculations.signalToNoiseRatio(original.points, processed.points); _peakSignalToNoiseRatio = ErrorCalculations.peakSignalToNoiseRatio(original.points, processed.points); _maximumDifference = ErrorCalculations.maxDifference(original.points, processed.points); SaveResultsCommand = new RelayCommand(SaveResults); RememberResultsCommand = new RelayCommand(RememberResults); }
public static double GetError(INeuralNetwork nn, IList <InputOutput> testSet) { var error = 0.0; foreach (var inputOutput in testSet) { var result = nn.FeedForward(inputOutput.Input); error += ErrorCalculations.CrossEntropyError(inputOutput.Output, result.Output); } return(error / testSet.Count); }
public static double GetMeanSquareError(double[] expected, double[] actual) { return(ErrorCalculations.MeanSquareError(expected, actual)); }
public static double GetCrossEntropyError(double[] expected, double[] actual) { return(ErrorCalculations.CrossEntropyError(expected, actual)); }