public void When_Forward_Pass_Invoked_Then_Output_Is_Calculated_Correctly()
{
var testObject = NeuralNetTestSetup.GetConfiguredNet();
var output = testObject.ForwardPass(new[] { 0.05, 0.10 });
output.Should().Equal(new[] { 0.75136507, 0.772928465 }, AreEqualApproximately);
}
public void When_Total_Error_Calculated_Then_It_Is_Correct()
{
var testObject = NeuralNetTestSetup.GetConfiguredNet();
var trainingSet = new TrainingSet(new[] { new TrainingSample(new[] { 0.05, 0.10 }, new[] { 0.01, 0.99 }) });
var totalError = ErrorFunctions.TotalError(testObject, trainingSet);
totalError.Should().BeApproximately(0.298371109, Precision);
}
//[InlineData(10000, 0.0000351085)]
public void When_Then(int iterationsCount, double expectedError)
{
var net = NeuralNetTestSetup.GetConfiguredNet();
var trainingSet = new TrainingSet(new[] { new TrainingSample(new[] { 0.05, 0.10 }, new[] { 0.01, 0.99 }) });
_trainingCfg = new TrainingConfiguration {
LearningRate = 0.5, MaxEpoch = iterationsCount
};
Backpropagation.Train(net, _trainingCfg, trainingSet, _ => { });
var actualError = ErrorFunctions.TotalError(net, trainingSet);
actualError.Should().BeApproximately(expectedError, Precision);
}
