public void Execute(IExampleInterface app)
{
this.app = app;
SetupInput();
var pattern = new ART1Pattern();
pattern.InputNeurons = INPUT_NEURONS;
pattern.OutputNeurons = OUTPUT_NEURONS;
var network = (ART1)pattern.Generate();
for (int i = 0; i < PATTERN.Length; i++)
{
var dataIn = new BiPolarMLData(input[i]);
var dataOut = new BiPolarMLData(OUTPUT_NEURONS);
network.Compute(dataIn, dataOut);
if (network.HasWinner)
{
app.WriteLine(PATTERN[i] + " - " + network.Winner);
}
else
{
app.WriteLine(PATTERN[i] + " - new Input and all Classes exhausted");
}
}
}
public void Execute(IExampleInterface app)
{
this.app = app;
// Create the neural network.
BasicLayer hopfield;
var network = new HopfieldNetwork(4);
// This pattern will be trained
bool[] pattern1 = { true, true, false, false };
// This pattern will be presented
bool[] pattern2 = { true, false, false, false };
IMLData result;
var data1 = new BiPolarMLData(pattern1);
var data2 = new BiPolarMLData(pattern2);
var set = new BasicMLDataSet();
set.Add(data1);
// train the neural network with pattern1
app.WriteLine("Training Hopfield network with: "
+ FormatBoolean(data1));
network.AddPattern(data1);
// present pattern1 and see it recognized
result = network.Compute(data1);
app.WriteLine("Presenting pattern:" + FormatBoolean(data1)
+ ", and got " + FormatBoolean(result));
// Present pattern2, which is similar to pattern 1. Pattern 1
// should be recalled.
result = network.Compute(data2);
app.WriteLine("Presenting pattern:" + FormatBoolean(data2)
+ ", and got " + FormatBoolean(result));
}
public void Execute(IExampleInterface app)
{
this.app = app;
// Create the neural network.
BasicLayer hopfield;
var network = new HopfieldNetwork(4);
// This pattern will be trained
bool[] pattern1 = {true, true, false, false};
// This pattern will be presented
bool[] pattern2 = {true, false, false, false};
IMLData result;
var data1 = new BiPolarMLData(pattern1);
var data2 = new BiPolarMLData(pattern2);
var set = new BasicMLDataSet();
set.Add(data1);
// train the neural network with pattern1
app.WriteLine("Training Hopfield network with: "
+ FormatBoolean(data1));
network.AddPattern(data1);
// present pattern1 and see it recognized
result = network.Compute(data1);
app.WriteLine("Presenting pattern:" + FormatBoolean(data1)
+ ", and got " + FormatBoolean(result));
// Present pattern2, which is similar to pattern 1. Pattern 1
// should be recalled.
result = network.Compute(data2);
app.WriteLine("Presenting pattern:" + FormatBoolean(data2)
+ ", and got " + FormatBoolean(result));
}
public void Execute(IExampleInterface app)
{
this.app = app;
IMLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
BasicNetwork network = EncogUtility.SimpleFeedForward(2, 6, 0, 1, false);
EncogUtility.TrainToError(network, trainingSet, 0.01);
double error = network.CalculateError(trainingSet);
EncogDirectoryPersistence.SaveObject(new FileInfo(FILENAME), network);
double error2 = network.CalculateError(trainingSet);
app.WriteLine("Error before save to EG: " + Format.FormatPercent(error));
app.WriteLine("Error before after to EG: " + Format.FormatPercent(error2));
}
public void TrainInstar(CPNNetwork network, IMLDataSet training)
{
int epoch = 1;
IMLTrain train = new TrainInstar(network, training, 0.1, true);
for (int i = 0; i < 1000; i++)
{
train.Iteration();
app.WriteLine("Training instar, Epoch #" + epoch);
epoch++;
}
}
/// <summary>
/// Display the cities in the final path.
/// </summary>
public void DisplaySolution()
{
int[] path = anneal.Array;
for (int i = 0; i < path.Length; i++)
{
if (i != 0)
{
app.Write(">");
}
app.Write("" + path[i]);
}
app.WriteLine("");
}
public void Execute(IExampleInterface app)
{
this.app = app;
this.app = app;
IMLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
BasicNetwork network = EncogUtility.SimpleFeedForward(2, 6, 0, 1, false);
EncogUtility.TrainToError(network, trainingSet, 0.01);
double error = network.CalculateError(trainingSet);
SerializeObject.Save("encog.ser", network);
network = (BasicNetwork) SerializeObject.Load("encog.ser");
double error2 = network.CalculateError(trainingSet);
app.WriteLine("Error before save to ser: " + Format.FormatPercent(error));
app.WriteLine("Error before after to ser: " + Format.FormatPercent(error2));
}
public void Execute(IExampleInterface app)
{
int inputNeurons = CHAR_WIDTH * CHAR_HEIGHT;
int outputNeurons = DIGITS.Length;
var pattern = new ADALINEPattern();
pattern.InputNeurons = inputNeurons;
pattern.OutputNeurons = outputNeurons;
var network = (BasicNetwork)pattern.Generate();
(new RangeRandomizer(-0.5, 0.5)).Randomize(network);
// train it
IMLDataSet training = GenerateTraining();
IMLTrain train = new TrainAdaline(network, training, 0.01);
int epoch = 1;
do
{
train.Iteration();
app.WriteLine("Epoch #" + epoch + " Error:" + train.Error);
epoch++;
} while (train.Error > 0.01);
//
app.WriteLine("Error:" + network.CalculateError(training));
// test it
for (int i = 0; i < DIGITS.Length; i++)
{
int output = network.Winner(Image2data(DIGITS[i]));
for (int j = 0; j < CHAR_HEIGHT; j++)
{
if (j == CHAR_HEIGHT - 1)
{
app.WriteLine(DIGITS[i][j] + " -> " + output);
}
else
{
app.WriteLine(DIGITS[i][j]);
}
}
app.WriteLine();
}
}
public void Execute(IExampleInterface app)
{
this.app = app;
IMLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
BasicNetwork network = EncogUtility.SimpleFeedForward(2, 6, 0, 1, false);
EncogUtility.TrainToError(network, trainingSet, 0.01);
double error = network.CalculateError(trainingSet);
EncogDirectoryPersistence.SaveObject(new FileInfo(FILENAME), network);
double error2 = network.CalculateError(trainingSet);
app.WriteLine("Error before save to EG: " + Format.FormatPercent(error));
app.WriteLine("Error before after to EG: " + Format.FormatPercent(error2));
}
private double TrainNetwork(String what, BasicNetwork network, IMLDataSet trainingSet)
{
// train the neural network
ICalculateScore score = new TrainingSetScore(trainingSet);
IMLTrain trainAlt = new NeuralSimulatedAnnealing(
network, score, 10, 2, 100);
IMLTrain trainMain = new Backpropagation(network, trainingSet, 0.00001, 0.0);
var stop = new StopTrainingStrategy();
trainMain.AddStrategy(new Greedy());
trainMain.AddStrategy(new HybridStrategy(trainAlt));
trainMain.AddStrategy(stop);
int epoch = 0;
while (!stop.ShouldStop())
{
trainMain.Iteration();
app.WriteLine("Training " + what + ", Epoch #" + epoch + " Error:" + trainMain.Error);
epoch++;
}
return(trainMain.Error);
}
private double TrainNetwork(String what, BasicNetwork network, IMLDataSet trainingSet, string Method)
{
// train the neural network
ICalculateScore score = new TrainingSetScore(trainingSet);
IMLTrain trainAlt = new NeuralSimulatedAnnealing(network, score, 10, 2, 100);
IMLTrain trainMain;
if (Method.Equals("Leven"))
{
Console.WriteLine("Using LevenbergMarquardtTraining");
trainMain = new LevenbergMarquardtTraining(network, trainingSet);
}
else
{
trainMain = new Backpropagation(network, trainingSet);
}
var stop = new StopTrainingStrategy();
trainMain.AddStrategy(new Greedy());
trainMain.AddStrategy(new HybridStrategy(trainAlt));
trainMain.AddStrategy(stop);
int epoch = 0;
while (!stop.ShouldStop())
{
trainMain.Iteration();
app.WriteLine("Training " + what + ", Epoch #" + epoch + " Error:" + trainMain.Error);
epoch++;
}
return(trainMain.Error);
}
public void Execute(IExampleInterface app)
{
this.app = app;
var pattern = new BAMPattern();
pattern.F1Neurons = INPUT_NEURONS;
pattern.F2Neurons = OUTPUT_NEURONS;
var network = (BAMNetwork)pattern.Generate();
// train
for (int i = 0; i < NAMES.Length; i++)
{
network.AddPattern(
StringToBipolar(NAMES[i]),
StringToBipolar(PHONES[i]));
}
// test
for (int i = 0; i < NAMES.Length; i++)
{
var data = new NeuralDataMapping(
StringToBipolar(NAMES[i]),
RandomBiPolar(OUT_CHARS * BITS_PER_CHAR));
RunBAM(network, data);
}
app.WriteLine();
for (int i = 0; i < PHONES.Length; i++)
{
var data = new NeuralDataMapping(
StringToBipolar(PHONES[i]),
RandomBiPolar(IN_CHARS * BITS_PER_CHAR));
RunBAM(network, data);
}
app.WriteLine();
for (int i = 0; i < NAMES.Length; i++)
{
var data = new NeuralDataMapping(
StringToBipolar(NAMES2[i]),
RandomBiPolar(OUT_CHARS * BITS_PER_CHAR));
RunBAM(network, data);
}
}
public void Execute(IExampleInterface app)
{
this.app = app;
var temp = new TemporalXOR();
IMLDataSet trainingSet = temp.Generate(100);
var jordanNetwork = (BasicNetwork) CreateJordanNetwork();
var feedforwardNetwork = (BasicNetwork) CreateFeedforwardNetwork();
double elmanError = TrainNetwork("Jordan", jordanNetwork, trainingSet);
double feedforwardError = TrainNetwork("Feedforward", feedforwardNetwork, trainingSet);
app.WriteLine("Best error rate with Jordan Network: " + elmanError);
app.WriteLine("Best error rate with Feedforward Network: " + feedforwardError);
app.WriteLine("Jordan will perform only marginally better than feedforward.\nThe more output neurons, the better performance a Jordan will give.");
}
public void Execute(IExampleInterface app)
{
this.app = app;
var temp = new TemporalXOR();
IMLDataSet trainingSet = temp.Generate(100);
var jordanNetwork = (BasicNetwork)CreateJordanNetwork();
var feedforwardNetwork = (BasicNetwork)CreateFeedforwardNetwork();
double elmanError = TrainNetwork("Jordan", jordanNetwork, trainingSet);
double feedforwardError = TrainNetwork("Feedforward", feedforwardNetwork, trainingSet);
app.WriteLine("Best error rate with Jordan Network: " + elmanError);
app.WriteLine("Best error rate with Feedforward Network: " + feedforwardError);
app.WriteLine("Jordan will perform only marginally better than feedforward.\nThe more output neurons, the better performance a Jordan will give.");
}
public void Execute(IExampleInterface app)
{
this.app = app;
this.app = app;
IMLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
BasicNetwork network = EncogUtility.SimpleFeedForward(2, 6, 0, 1, false);
EncogUtility.TrainToError(network, trainingSet, 0.01);
double error = network.CalculateError(trainingSet);
SerializeObject.Save("encog.ser", network);
network = (BasicNetwork)SerializeObject.Load("encog.ser");
double error2 = network.CalculateError(trainingSet);
app.WriteLine("Error before save to ser: " + Format.FormatPercent(error));
app.WriteLine("Error before after to ser: " + Format.FormatPercent(error2));
}
public void Execute(IExampleInterface app)
{
this.app = app;
var temp = new TemporalXOR();
IMLDataSet trainingSet = temp.Generate(100);
var elmanNetwork = (BasicNetwork) CreateElmanNetwork();
var feedforwardNetwork = (BasicNetwork) CreateFeedforwardNetwork();
double elmanError = TrainNetwork("Elman", elmanNetwork, trainingSet);
double feedforwardError = TrainNetwork("Feedforward", feedforwardNetwork, trainingSet);
app.WriteLine("Best error rate with Elman Network: " + elmanError);
app.WriteLine("Best error rate with Feedforward Network: " + feedforwardError);
app.WriteLine("(Elman should outperform feed forward)");
app.WriteLine("If your results are not as good, try rerunning, or perhaps training longer.");
}
public void RunBAM(BAMNetwork network, NeuralDataMapping data)
{
var line = new StringBuilder();
line.Append(MappingToString(data));
network.Compute(data);
line.Append(" | ");
line.Append(MappingToString(data));
app.WriteLine(line.ToString());
}
public void Execute(IExampleInterface app)
{
this.app = app;
var pattern = new BoltzmannPattern();
pattern.InputNeurons = NEURON_COUNT;
var network = (BoltzmannMachine) pattern.Generate();
CreateCities();
CalculateWeights(network);
network.Temperature = 100;
do
{
network.EstablishEquilibrium();
app.WriteLine(network.Temperature + " : " + DisplayTour(network.CurrentState));
network.DecreaseTemperature(0.99);
} while (!IsValidTour(network.CurrentState));
app.WriteLine("Final Length: " + LengthOfTour(network.CurrentState));
}
private void ProcessCreateTraining()
{
String strWidth = GetArg("width");
String strHeight = GetArg("height");
String strType = GetArg("type");
downsampleHeight = int.Parse(strWidth);
downsampleWidth = int.Parse(strHeight);
if (strType.Equals("RGB"))
{
downsample = new RGBDownsample();
}
else
{
downsample = new SimpleIntensityDownsample();
}
training = new ImageMLDataSet(downsample, false, 1, -1);
app.WriteLine("Training set created");
}
public void Execute(IExampleInterface app)
{
this.app = app;
var pattern = new BoltzmannPattern();
pattern.InputNeurons = NEURON_COUNT;
var network = (BoltzmannMachine)pattern.Generate();
CreateCities();
CalculateWeights(network);
network.Temperature = 100;
do
{
network.EstablishEquilibrium();
app.WriteLine(network.Temperature + " : " + DisplayTour(network.CurrentState));
network.DecreaseTemperature(0.99);
} while (!IsValidTour(network.CurrentState));
app.WriteLine("Final Length: " + LengthOfTour(network.CurrentState));
}
public void Execute(IExampleInterface app)
{
this.app = app;
var temp = new TemporalXOR();
IMLDataSet trainingSet = temp.Generate(100);
if (app.Args.Length > 0)
{
trainingSet = temp.Generate(Convert.ToInt16(app.Args[0]));
}
var elmanNetwork = (BasicNetwork)CreateElmanNetwork(trainingSet.InputSize);
var feedforwardNetwork = (BasicNetwork)CreateFeedforwardNetwork(trainingSet.InputSize);
double elmanError = TrainNetwork("Elman", elmanNetwork, trainingSet, "Leven");
double feedforwardError = TrainNetwork("Feedforward", feedforwardNetwork, trainingSet, "Leven");
app.WriteLine("Best error rate with Elman Network: " + elmanError);
app.WriteLine("Best error rate with Feedforward Network: " + feedforwardError);
app.WriteLine("(Elman should outperform feed forward)");
app.WriteLine("If your results are not as good, try rerunning, or perhaps training longer.");
}
public void Execute(IExampleInterface app)
{
this.app = app;
SetupInput();
var pattern = new ART1Pattern();
pattern.InputNeurons = INPUT_NEURONS;
pattern.OutputNeurons = OUTPUT_NEURONS;
var network = (ART1) pattern.Generate();
for (int i = 0; i < PATTERN.Length; i++)
{
var dataIn = new BiPolarMLData(input[i]);
var dataOut = new BiPolarMLData(OUTPUT_NEURONS);
network.Compute(dataIn, dataOut);
if (network.HasWinner)
{
app.WriteLine(PATTERN[i] + " - " + network.Winner);
}
else
{
app.WriteLine(PATTERN[i] + " - new Input and all Classes exhausted");
}
}
}
public void Execute(IExampleInterface app)
{
int inputNeurons = CHAR_WIDTH*CHAR_HEIGHT;
int outputNeurons = DIGITS.Length;
var pattern = new ADALINEPattern();
pattern.InputNeurons = inputNeurons;
pattern.OutputNeurons = outputNeurons;
var network = (BasicNetwork) pattern.Generate();
(new RangeRandomizer(-0.5, 0.5)).Randomize(network);
// train it
IMLDataSet training = GenerateTraining();
IMLTrain train = new TrainAdaline(network, training, 0.01);
int epoch = 1;
do
{
train.Iteration();
app.WriteLine("Epoch #" + epoch + " Error:" + train.Error);
epoch++;
} while (train.Error > 0.01);
//
app.WriteLine("Error:" + network.CalculateError(training));
// test it
for (int i = 0; i < DIGITS.Length; i++)
{
int output = network.Winner(Image2data(DIGITS[i]));
for (int j = 0; j < CHAR_HEIGHT; j++)
{
if (j == CHAR_HEIGHT - 1)
app.WriteLine(DIGITS[i][j] + " -> " + output);
else
app.WriteLine(DIGITS[i][j]);
}
app.WriteLine();
}
}
public void Execute(IExampleInterface app)
{
this.app = app;
var pattern = new BAMPattern();
pattern.F1Neurons = INPUT_NEURONS;
pattern.F2Neurons = OUTPUT_NEURONS;
var network = (BAMNetwork) pattern.Generate();
// train
for (int i = 0; i < NAMES.Length; i++)
{
network.AddPattern(
StringToBipolar(NAMES[i]),
StringToBipolar(PHONES[i]));
}
// test
for (int i = 0; i < NAMES.Length; i++)
{
var data = new NeuralDataMapping(
StringToBipolar(NAMES[i]),
RandomBiPolar(OUT_CHARS*BITS_PER_CHAR));
RunBAM(network, data);
}
app.WriteLine();
for (int i = 0; i < PHONES.Length; i++)
{
var data = new NeuralDataMapping(
StringToBipolar(PHONES[i]),
RandomBiPolar(IN_CHARS*BITS_PER_CHAR));
RunBAM(network, data);
}
app.WriteLine();
for (int i = 0; i < NAMES.Length; i++)
{
var data = new NeuralDataMapping(
StringToBipolar(NAMES2[i]),
RandomBiPolar(OUT_CHARS*BITS_PER_CHAR));
RunBAM(network, data);
}
}
