public void CorrectRunThreeInputs()
{
int numberOfBanks = 3;
WeightedCombiner layer = new WeightedCombiner(new WeightsMatrix(new double[, ] {
{ 2, 3, 5 }
}));
WeightedCombinerBank bank = new WeightedCombinerBank(layer, numberOfBanks);
NetworkVector input = new NetworkVector(new double[] { 7, 7, 7, 11, 11, 11, 13, 13, 13 });
NetworkVector outputcheck = new NetworkVector(new double[] { 70, 110, 130 });
NetworkVector result = bank.Run(input);
Assert.AreEqual(outputcheck, result);
}
public void TrainOnline_WC_CorrectThreePasses()
{
WeightsMatrix matrix = new WeightsMatrix(new double[, ] {
{ 1, 1 }
});
WeightedCombiner wc = new WeightedCombiner(matrix);
TrainingCollection trainingVectors = new TrainingCollection
{
new VectorPair(
new NetworkVector(new double[] { 0, 0 }),
new NetworkVector(new double[] { 1 })
),
new VectorPair(
new NetworkVector(new double[] { 1, 0 }),
new NetworkVector(new double[] { 0 })
),
new VectorPair(
new NetworkVector(new double[] { 0, 1 }),
new NetworkVector(new double[] { 0 })
),
new VectorPair(
new NetworkVector(new double[] { 1, 1 }),
new NetworkVector(new double[] { 1 })
)
};
Trainer trainer = new Trainer(wc, new SquaredError(), new GradientDescent());
foreach (TrainingCollection tc in trainingVectors.AsSingletons())
{
trainer.Train(tc);
}
foreach (TrainingCollection tc in trainingVectors.AsSingletons())
{
trainer.Train(tc);
}
foreach (TrainingCollection tc in trainingVectors.AsSingletons())
{
trainer.Train(tc);
}
WeightsMatrix weightsCheck = new WeightsMatrix(new double[, ] {
{ 3, 7 }
});
NetworkVector biasesCheck = new NetworkVector(new double[] { -1 });
Assert.AreEqual(biasesCheck, wc.Biases);
Assert.AreEqual(weightsCheck, wc.Weights);
}
public void CannotRunWeightedCombinerBankWithBadInputSize()
{
int numberOfBanks = 3;
WeightedCombiner layer = new WeightedCombiner(new WeightsMatrix(new double[, ] {
{ 1 }
}));
WeightedCombinerBank bank = new WeightedCombinerBank(layer, numberOfBanks);
NetworkVector badInput = new NetworkVector(2);
try
{
bank.Run(badInput);
Assert.Fail("WeightedCombinerBank.Run failed to throw an ArgumentException for input of the wrong size.");
}
catch (ArgumentException) { }
}
public void CannotBackPropagateWeightedCombinerBankWithBadOutputGradientSize()
{
int numberOfBanks = 3;
WeightedCombiner layer = new WeightedCombiner(new WeightsMatrix(new double[, ] {
{ 1 }
}));
WeightedCombinerBank bank = new WeightedCombinerBank(layer, numberOfBanks);
NetworkVector badGradient = new NetworkVector(2);
try
{
bank.BackPropagate(badGradient, new NetworkVector(3));
Assert.Fail("WeightedCombinerBank.BackPropagate failed to throw an ArgumentException for outputgradient of the wrong size.");
}
catch (ArgumentException) { }
}
public void BatchTrainCorrectThreePasses_WC()
{
WeightsMatrix matrix = new WeightsMatrix(new double[, ] {
{ 1, 1 }
});
WeightedCombiner wc = new WeightedCombiner(matrix);
TrainingCollection trainingVectors = new TrainingCollection
{
new VectorPair(
new NetworkVector(new double[] { 0, 0 }),
new NetworkVector(new double[] { 1 })
),
new VectorPair(
new NetworkVector(new double[] { 1, 0 }),
new NetworkVector(new double[] { 0 })
),
new VectorPair(
new NetworkVector(new double[] { 0, 1 }),
new NetworkVector(new double[] { 0 })
),
new VectorPair(
new NetworkVector(new double[] { 1, 1 }),
new NetworkVector(new double[] { 1 })
)
};
Trainer trainer = new Trainer(wc, new SquaredError(), new GradientDescent());
trainer.Train(trainingVectors);
trainer.Train(trainingVectors);
trainer.Train(trainingVectors);
WeightsMatrix weightsCheck = new WeightsMatrix(new double[, ] {
{ -37, -37 }
});
NetworkVector biasesCheck = new NetworkVector(new double[] { -62 });
Assert.AreEqual(biasesCheck, wc.Biases);
Assert.AreEqual(weightsCheck, wc.Weights);
}
public WeightedCombinerTests()
{
wc_1 = new WeightedCombiner(matrix_1);
wc_1b = new WeightedCombiner(matrix_1, vector_1);
wc_2 = new WeightedCombiner(matrix_2, vector_2);
}
