public BackPropagationPerformanceComparisonContainer()
{
var neuralNetworkUnderTest =
NeuralNetwork
.For(NeuralNetworkContext.MaximumPrecision)
.WithInputLayer(neuronCount: 5, activationType: ActivationType.Sigmoid)
.WithHiddenLayer(neuronCount: 100, activationType: ActivationType.Sigmoid)
.WithHiddenLayer(neuronCount: 70, activationType: ActivationType.TanH)
.WithHiddenLayer(neuronCount: 40, activationType: ActivationType.TanH)
.WithHiddenLayer(neuronCount: 100, activationType: ActivationType.Sigmoid)
.WithOutputLayer(neuronCount: 2, activationType: ActivationType.Sigmoid)
.Build();
trainingData = new[] {
TrainingDataSet.For(new [] { 0.78, 0.99, 0.67, 0.72, 0.22 }, new [] { 0.12, 0.14 })
};
multiThreadedController = TrainingController.For(
BackPropagation
.WithConfiguration(neuralNetworkUnderTest, ParallelOptionsExtensions.UnrestrictedMultiThreadedOptions));
singleThreadedController = TrainingController.For(
BackPropagation
.WithConfiguration(neuralNetworkUnderTest, ParallelOptionsExtensions.SingleThreadedOptions));
}
public async Task TrainConfiguredNetworkForEpochs(
int epochs,
NeuralNetworkTrainingConfiguration trainingConfig)
{
var trainingData = dataProvider.TrainingData
.Select(transaction => transaction.ToTrainingData())
.ToList();
await TrainingController.For(BackPropagation.WithConfiguration(
networkAccessor.TargetNetwork,
ParallelOptionsExtensions.MultiThreadedOptions(trainingConfig.ThreadCount),
trainingConfig.LearningRate,
trainingConfig.Momentum))
.TrainForEpochsOrErrorThresholdMet(trainingData, epochs, trainingConfig.MinimumErrorThreshold);
}
public async void CanSuccessfullySolveXorProblemTrainingForErrorThreshold()
{
var neuralNetwork = NeuralNetwork.For(NeuralNetworkContext.MaximumPrecision)
.WithInputLayer(neuronCount: 2, activationType: ActivationType.Sigmoid)
.WithHiddenLayer(neuronCount: 2, activationType: ActivationType.TanH)
.WithOutputLayer(neuronCount: 1, activationType: ActivationType.Sigmoid)
.Build();
await TrainingController
.For(BackPropagation.WithConfiguration(
neuralNetwork,
ParallelOptionsExtensions.UnrestrictedMultiThreadedOptions,
learningRate: 0.4,
momentum: 0.9))
.TrainForErrorThreshold(XorTrainingData(), minimumErrorThreshold: 0.01);
AssertPredictionsForTrainedNeuralNetwork(neuralNetwork);
}
public async void CanSuccessfullySolveIrisProblemTrainingForEpochs()
{
var neuralNetwork = NeuralNetwork.For(NeuralNetworkContext.MaximumPrecision)
.WithInputLayer(neuronCount: 4, activationType: ActivationType.Sigmoid)
.WithHiddenLayer(neuronCount: 8, activationType: ActivationType.Sigmoid)
.WithHiddenLayer(neuronCount: 5, activationType: ActivationType.Sigmoid)
.WithOutputLayer(neuronCount: 3, activationType: ActivationType.TanH)
.Build();
await TrainingController
.For(BackPropagation.WithConfiguration(
neuralNetwork,
ParallelOptionsExtensions.UnrestrictedMultiThreadedOptions,
learningRate: 1.15,
momentum: 0.4))
.TrainForEpochs(IrisDataSet.TrainingData, maximumEpochs: 1000);
AssertPredictionsForTrainedNeuralNetwork(neuralNetwork);
}
private async void button3_Click(object sender, EventArgs e)
{
progressBar1.Value = 20;
neuralNetwork = NeuralNetwork.For(NeuralNetworkContext.MaximumPrecision)
.WithInputLayer(neuronCount: 64, activationType: ActivationType.Sigmoid)
.WithHiddenLayer(neuronCount: 10, activationType: ActivationType.Sigmoid)
.WithOutputLayer(neuronCount: 3, activationType: ActivationType.Sigmoid)
.Build();
progressBar1.Value = 40;
await TrainingController
.For(BackPropagation.WithConfiguration(
neuralNetwork,
ParallelOptionsExtensions.UnrestrictedMultiThreadedOptions,
learningRate: 1.8,
momentum: 0.9))
.TrainForEpochsOrErrorThresholdMet(GetMyTrainingData(), maximumEpochs: 5000, errorThreshold: 0.05);
progressBar1.Value = 100;
button4.Visible = true;
progressBar1.Visible = false;
}
public static void Main(string[] args)
{
ConfigureLogging();
var neuralNetwork = NeuralNetwork.For(NeuralNetworkContext.MaximumPrecision)
.WithInputLayer(neuronCount: 2, activationType: ActivationType.Sigmoid)
.WithHiddenLayer(neuronCount: 5, activationType: ActivationType.TanH)
.WithOutputLayer(neuronCount: 1, activationType: ActivationType.Sigmoid)
.Build();
TrainingController
.For(BackPropagation.WithConfiguration(
neuralNetwork,
ParallelOptionsExtensions.UnrestrictedMultiThreadedOptions,
learningRate: 0.6,
momentum: 0.9))
.TrainForEpochsOrErrorThresholdMet(GetXorTrainingData(), maximumEpochs: 5000, errorThreshold: 0.001)
.GetAwaiter()
.GetResult();
MakeExamplePredictions(neuralNetwork);
}
