/// <summary>
/// Generate the network.
/// </summary>
/// <returns>The generated network.</returns>
public BasicNetwork Generate()
{
ILayer input, instar, outstar;
int y = PatternConst.START_Y;
BasicNetwork network = new BasicNetwork();
network.AddLayer(input = new BasicLayer(new ActivationLinear(), false, this.inputCount));
network.AddLayer(instar = new BasicLayer(new ActivationCompetitive(), false, this.instarCount));
network.AddLayer(outstar = new BasicLayer(new ActivationLinear(), false, this.outstarCount));
network.Structure.FinalizeStructure();
network.Reset();
input.X = PatternConst.START_X;
input.Y = y;
y += PatternConst.INC_Y;
instar.X = PatternConst.START_X;
instar.Y = y;
y += PatternConst.INC_Y;
outstar.X = PatternConst.START_X;
outstar.Y = y;
// tag as needed
network.TagLayer(BasicNetwork.TAG_INPUT, input);
network.TagLayer(BasicNetwork.TAG_OUTPUT, outstar);
network.TagLayer(CPNPattern.TAG_INSTAR, instar);
network.TagLayer(CPNPattern.TAG_OUTSTAR, outstar);
return network;
}
/// <summary>
/// Generate the Hopfield neural network.
/// </summary>
/// <returns>The generated network.</returns>
public BasicNetwork Generate()
{
ILayer layer = new BasicLayer(new ActivationBiPolar(), false,
this.neuronCount);
BasicNetwork result = new BasicNetwork(new HopfieldLogic());
result.AddLayer(layer);
layer.AddNext(layer);
layer.X = PatternConst.START_X;
layer.Y = PatternConst.START_Y;
result.Structure.FinalizeStructure();
result.Reset();
return result;
}
/// <summary>
/// Generate the RSOM network.
/// </summary>
/// <returns>The neural network.</returns>
public BasicNetwork Generate()
{
ILayer input = new BasicLayer(new ActivationLinear(), false,
this.inputNeurons);
ILayer output = new BasicLayer(new ActivationLinear(), false,
this.outputNeurons);
int y = PatternConst.START_Y;
BasicNetwork network = new BasicNetwork();
network.AddLayer(input);
network.AddLayer(output);
input.X = PatternConst.START_X;
output.X = PatternConst.START_X;
input.Y = y;
y += PatternConst.INC_Y;
output.Y = y;
network.Logic = new SOMLogic();
network.Structure.FinalizeStructure();
network.Reset();
return network;
}
/// <summary>
/// Generate a Jordan neural network.
/// </summary>
/// <returns>A Jordan neural network.</returns>
public BasicNetwork Generate()
{
// construct an Jordan type network
ILayer input = new BasicLayer(this.activation, false,
this.inputNeurons);
ILayer hidden = new BasicLayer(this.activation, true,
this.hiddenNeurons);
ILayer output = new BasicLayer(this.activation, true,
this.outputNeurons);
ILayer context = new ContextLayer(this.outputNeurons);
BasicNetwork network = new BasicNetwork();
network.AddLayer(input);
network.AddLayer(hidden);
network.AddLayer(output);
output.AddNext(context, SynapseType.OneToOne);
context.AddNext(hidden);
int y = PatternConst.START_Y;
input.X = PatternConst.START_X;
input.Y = y;
y += PatternConst.INC_Y;
hidden.X = PatternConst.START_X;
hidden.Y = y;
context.X = PatternConst.INDENT_X;
context.Y = y;
y += PatternConst.INC_Y;
output.X = PatternConst.START_X;
output.Y = y;
network.Structure.FinalizeStructure();
network.Reset();
return network;
}
/// <summary>
/// This is based off of this article:
/// http://www.codeproject.com/Articles/54575/An-Introduction-to-Encog-Neural-Networks-for-C
/// </summary>
/// <remarks>
/// Go here for documentation of encog:
/// http://www.heatonresearch.com/wiki
///
/// Download link:
/// https://github.com/encog/encog-dotnet-core/releases
/// </remarks>
private void btnXOR_Click(object sender, RoutedEventArgs e)
{
try
{
_trainingData = null;
_results = null;
BasicNetwork network = new BasicNetwork();
#region Create nodes
// Create the network's nodes
//NOTE: Using ActivationSigmoid, because there are no negative values. If there were negative, use ActivationTANH
//http://www.heatonresearch.com/wiki/Activation_Function
//NOTE: ActivationSigmoid (0 to 1) and ActivationTANH (-1 to 1) are pure but slower. A cruder but faster function is ActivationElliott (0 to 1) and ActivationElliottSymmetric (-1 to 1)
//http://www.heatonresearch.com/wiki/Elliott_Activation_Function
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 2)); // input layer
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 6)); // hidden layer
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 1)); // output layer
network.Structure.FinalizeStructure();
// Randomize the links
network.Reset();
#endregion
#region Training data
// Neural networks must be trained before they are of any use. To train this neural network, we must provide training
// data. The training data is the truth table for the XOR operator. The XOR has the following inputs:
double[][] xor_input = new[]
{
new[] { 0d, 0d },
new[] { 1d, 0d },
new[] { 0d, 1d },
new[] { 1d, 1d },
};
// And the expected outputs
double[][] xor_ideal_output = new[]
{
new[] { 0d },
new[] { 1d },
new[] { 1d },
new[] { 0d },
};
_trainingData = GetDrawDataFromTrainingData(xor_input, xor_ideal_output);
#endregion
#region Train network
INeuralDataSet trainingSet = new BasicNeuralDataSet(xor_input, xor_ideal_output);
// This is a good general purpose training algorithm
//http://www.heatonresearch.com/wiki/Training
ITrain train = new ResilientPropagation(network, trainingSet);
List <double> log = new List <double>();
int trainingIteration = 1;
do
{
train.Iteration();
log.Add(train.Error);
trainingIteration++;
} while ((trainingIteration < 2000) && (train.Error > 0.001));
// Paste this into excel and chart it to see the error trend
string logExcel = string.Join("\r\n", log);
#endregion
#region Test
//NOTE: I initially ran a bunch of tests, but the network always returns exactly the same result when given the same inputs
//var test = Enumerable.Range(0, 1000).
// Select(o => new { In1 = _rand.Next(2), In2 = _rand.Next(2) }).
var test = xor_input.
Select(o => new { In1 = Convert.ToInt32(o[0]), In2 = Convert.ToInt32(o[1]) }).
Select(o => new
{
o.In1,
o.In2,
Expected = XOR(o.In1, o.In2),
NN = CallNN(network, o.In1, o.In2),
}).
Select(o => new { o.In1, o.In2, o.Expected, o.NN, Error = Math.Abs(o.Expected - o.NN) }).
OrderByDescending(o => o.Error).
ToArray();
#endregion
#region Test intermediate values
// It was only trained with inputs of 0 and 1. Let's see what it does with values in between
var intermediates = Enumerable.Range(0, 1000).
Select(o => new { In1 = _rand.NextDouble(), In2 = _rand.NextDouble() }).
Select(o => new
{
o.In1,
o.In2,
NN = CallNN(network, o.In1, o.In2),
}).
OrderBy(o => o.In1).
ThenBy(o => o.In2).
//OrderBy(o => o.NN).
ToArray();
#endregion
#region Serialize/Deserialize
// Serialize it
string weightDump = network.DumpWeights();
double[] dumpArray = weightDump.Split(',').
Select(o => double.Parse(o)).
ToArray();
//TODO: Shoot through the layers, and store in some custom structure that can be serialized, then walked through to rebuild on deserialize
//string[] layerDump = network.Structure.Layers.
// Select(o => o.ToString()).
// ToArray();
// Create a clone
BasicNetwork clone = new BasicNetwork();
clone.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 2));
clone.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 6));
clone.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 1));
clone.Structure.FinalizeStructure();
clone.DecodeFromArray(dumpArray);
// Test the clone
string cloneDump = clone.DumpWeights();
bool isSame = weightDump == cloneDump;
var cloneTests = xor_input.
Select(o => new
{
Input = o,
NN = CallNN(clone, o[0], o[1]),
}).ToArray();
#endregion
#region Store results
double[] matchValues = new[] { 0d, 1d };
double matchRange = .03; //+- 5% of target value would be considered a match
_results = intermediates.
Select(o => Tuple.Create(new Point(o.In1, o.In2), o.NN, IsMatch(o.NN, matchValues, matchRange))).
ToArray();
#endregion
}
catch (Exception ex)
{
MessageBox.Show(ex.ToString(), this.Title, MessageBoxButton.OK, MessageBoxImage.Error);
}
finally
{
RedrawResults();
}
}
/// <summary>
/// Generate the network.
/// </summary>
/// <returns>The generated network.</returns>
public BasicNetwork Generate()
{
ILayer layer = new BasicLayer(new ActivationBiPolar(), true,
this.neuronCount);
BasicNetwork result = new BasicNetwork(new BoltzmannLogic());
result.SetProperty(BoltzmannLogic.PROPERTY_ANNEAL_CYCLES, this.annealCycles);
result.SetProperty(BoltzmannLogic.PROPERTY_RUN_CYCLES, this.runCycles);
result.SetProperty(BoltzmannLogic.PROPERTY_TEMPERATURE, this.temperature);
result.AddLayer(layer);
layer.AddNext(layer);
layer.X = PatternConst.START_X;
layer.Y = PatternConst.START_Y;
result.Structure.FinalizeStructure();
result.Reset();
return result;
}
public void Execute(IExampleInterface app)
{
//Specify the number of dimensions and the number of neurons per dimension
int dimensions = 2;
int numNeuronsPerDimension = 7;
//Set the standard RBF neuron width.
//Literature seems to suggest this is a good default value.
double volumeNeuronWidth = 2.0 / numNeuronsPerDimension;
//RBF can struggle when it comes to flats at the edge of the sample space.
//We have added the ability to include wider neurons on the sample space boundary which greatly
//improves fitting to flats
bool includeEdgeRBFs = true;
#region Setup
//General setup is the same as before
RadialBasisPattern pattern = new RadialBasisPattern();
pattern.InputNeurons = dimensions;
pattern.OutputNeurons = 1;
//Total number of neurons required.
//Total number of Edges is calculated possibly for future use but not used any further here
int numNeurons = (int)Math.Pow(numNeuronsPerDimension, dimensions);
int numEdges = (int)(dimensions * Math.Pow(2, dimensions - 1));
pattern.AddHiddenLayer(numNeurons);
BasicNetwork network = pattern.Generate();
RadialBasisFunctionLayer rbfLayer = (RadialBasisFunctionLayer)network.GetLayer(RadialBasisPattern.RBF_LAYER);
network.Reset();
//Position the multidimensional RBF neurons, with equal spacing, within the provided sample space from 0 to 1.
rbfLayer.SetRBFCentersAndWidthsEqualSpacing(0, 1, RBFEnum.Gaussian, dimensions, volumeNeuronWidth, includeEdgeRBFs);
#endregion
//Create some training data that can not easily be represented by gaussians
//There are other training examples for both 1D and 2D
//Degenerate training data only provides outputs as 1 or 0 (averaging over all outputs for a given set of inputs would produce something approaching the smooth training data).
//Smooth training data provides true values for the provided input dimensions.
Create2DSmoothTainingDataGit();
//Create the training set and train.
INeuralDataSet trainingSet = new BasicNeuralDataSet(INPUT, IDEAL);
ITrain train = new SVDTraining(network, trainingSet);
//SVD is a single step solve
int epoch = 1;
do
{
train.Iteration();
Console.WriteLine("Epoch #" + epoch + " Error:" + train.Error);
epoch++;
} while ((epoch < 1) && (train.Error > 0.001));
// test the neural network
Console.WriteLine("Neural Network Results:");
//Create a testing array which may be to a higher resoltion than the original training data
Set2DTestingArrays(100);
trainingSet = new BasicNeuralDataSet(INPUT, IDEAL);
//Write out the results data
using (var sw = new System.IO.StreamWriter("results.csv", false))
{
foreach (INeuralDataPair pair in trainingSet)
{
INeuralData output = network.Compute(pair.Input);
//1D//sw.WriteLine(InverseScale(pair.Input[0]) + ", " + Chop(InverseScale(output[0])));// + ", " + pair.Ideal[0]);
sw.WriteLine(InverseScale(pair.Input[0]) + ", " + InverseScale(pair.Input[1]) + ", " + Chop(InverseScale(output[0])));// + ", " + pair.Ideal[0]);// + ",ideal=" + pair.Ideal[0]);
//3D//sw.WriteLine(InverseScale(pair.Input[0]) + ", " + InverseScale(pair.Input[1]) + ", " + InverseScale(pair.Input[2]) + ", " + Chop(InverseScale(output[0])));// + ", " + pair.Ideal[0]);// + ",ideal=" + pair.Ideal[0]);
//Console.WriteLine(pair.Input[0] + ", actual=" + output[0] + ",ideal=" + pair.Ideal[0]);
}
}
Console.WriteLine("\nFit output saved to results.csv");
Console.WriteLine("\nComplete - Please press the 'any' key to close.");
Console.ReadKey();
}
/// <summary>
/// Generate the RBF network.
/// </summary>
/// <returns>The neural network.</returns>
public BasicNetwork Generate()
{
ILayer input = new BasicLayer(new ActivationLinear(), false,
this.inputNeurons);
ILayer output = new BasicLayer(new ActivationLinear(), false, this.outputNeurons);
BasicNetwork network = new BasicNetwork();
RadialBasisFunctionLayer rbfLayer = new RadialBasisFunctionLayer(
this.hiddenNeurons);
network.AddLayer(input);
network.AddLayer(rbfLayer, SynapseType.Direct);
network.AddLayer(output);
network.Structure.FinalizeStructure();
network.Reset();
network.TagLayer(RBF_LAYER, rbfLayer);
rbfLayer.RandomizeRBFCentersAndWidths(this.inputNeurons, -1, 1, RBFEnum.Gaussian);
int y = PatternConst.START_Y;
input.X = PatternConst.START_X;
input.Y = y;
y += PatternConst.INC_Y;
rbfLayer.X = PatternConst.START_X;
rbfLayer.Y = y;
y += PatternConst.INC_Y;
output.X = PatternConst.START_X;
output.Y = y;
return network;
}
public static String TrainModel(MegasenaListResult dbl, int deepness)
{
var deep = deepness;
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, 6 * deep));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 5 * 6 * deep));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 5 * 6 * deep));
network.AddLayer(new BasicLayer(new ActivationLinear(), true, 6));
network.Structure.FinalizeStructure();
var learningInput = new double[deep][];
for (int i = 0; i < deep; ++i)
{
learningInput[i] = new double[deep * 6];
for (int j = 0, k = 0; j < deep; ++j)
{
var idx = 2 * deep - i - j;
var data = dbl[idx];
learningInput[i][k++] = (double)data.V1;
learningInput[i][k++] = (double)data.V2;
learningInput[i][k++] = (double)data.V3;
learningInput[i][k++] = (double)data.V4;
learningInput[i][k++] = (double)data.V5;
learningInput[i][k++] = (double)data.V6;
}
}
var learningOutput = new double[deep][];
for (int i = 0; i < deep; ++i)
{
var idx = deep - 1 - i;
var data = dbl[idx];
learningOutput[i] = new double[6]
{
(double)data.V1,
(double)data.V2,
(double)data.V3,
(double)data.V4,
(double)data.V5,
(double)data.V6
};
}
var trainingSet = new BasicMLDataSet(learningInput, learningOutput);
var train = new ResilientPropagation(network, trainingSet);
train.NumThreads = Environment.ProcessorCount;
START:
network.Reset();
RETRY:
var step = 0;
do
{
train.Iteration();
Console.WriteLine("Train Error: {0}", train.Error);
++step;
}while (train.Error > 0.001 && step < 20);
var passedCount = 0;
for (var i = 0; i < deep; ++i)
{
var should = new MegasenaResult(learningOutput[i]);
var inputn = new BasicMLData(6 * deep);
Array.Copy(learningInput[i], inputn.Data, inputn.Data.Length);
var comput = new MegasenaResult(((BasicMLData)network.Compute(inputn)).Data);
var passed = should.ToString() == comput.ToString();
if (passed)
{
Console.ForegroundColor = ConsoleColor.Green;
++passedCount;
}
else
{
Console.ForegroundColor = ConsoleColor.Red;
}
Console.WriteLine("{0} {1} {2} {3}",
should.ToString().PadLeft(17, ' '),
passed ? "==" : "!=",
comput.ToString().PadRight(17, ' '),
passed ? "PASS" : "FAIL");
Console.ResetColor();
}
var input = new BasicMLData(6 * deep);
for (int i = 0, k = 0; i < deep; ++i)
{
var idx = deep - 1 - i;
var data = dbl[idx];
input.Data[k++] = (double)data.V1;
input.Data[k++] = (double)data.V2;
input.Data[k++] = (double)data.V3;
input.Data[k++] = (double)data.V4;
input.Data[k++] = (double)data.V5;
input.Data[k++] = (double)data.V6;
}
var perfect = dbl[0];
var predict = new MegasenaResult(((BasicMLData)network.Compute(input)).Data);
Console.ForegroundColor = ConsoleColor.Yellow;
//Console.WriteLine("Predict: {0}", predict);
Console.ResetColor();
if (predict.IsOut())
{
goto START;
}
if ((double)passedCount < (deep * (double)9 / (double)10) ||
!predict.IsValid())
{
goto RETRY;
}
//Console.WriteLine("Press any key for close...");
//Console.ReadKey(true);
return(ReturnOrderedPredictResult(predict.ToString()));
}
/// <summary>
/// Generate the Elman neural network.
/// </summary>
/// <returns>The Elman neural network.</returns>
public BasicNetwork Generate()
{
int y = PatternConst.START_Y;
ILayer input = new BasicLayer(this.activation, false,
this.inputNeurons);
BasicNetwork result = new BasicNetwork();
result.AddLayer(input);
input.X = PatternConst.START_X;
input.Y = y;
y += PatternConst.INC_Y;
foreach (int count in this.hidden)
{
ILayer hidden = new BasicLayer(
this.activation, true, count);
result.AddLayer(hidden);
hidden.X = PatternConst.START_X;
hidden.Y = y;
y += PatternConst.INC_Y;
}
ILayer output = new BasicLayer(this.activation, true,
this.outputNeurons);
result.AddLayer(output);
output.X = PatternConst.START_X;
output.Y = y;
y += PatternConst.INC_Y;
result.Structure.FinalizeStructure();
result.Reset();
return result;
}
/// <summary>
/// Run the example.
/// </summary>
public void Process()
{
// read the iris data from the resources
var assembly = Assembly.GetExecutingAssembly();
var res = assembly.GetManifestResourceStream("AIFH_Vol3.Resources.auto-mpg.data.csv");
// did we fail to read the resouce
if (res == null)
{
Console.WriteLine("Can't read auto MPG data from embedded resources.");
return;
}
// load the data
var istream = new StreamReader(res);
var ds = DataSet.Load(istream);
istream.Close();
// The following ranges are setup for the Auto MPG data set. If you wish to normalize other files you will
// need to modify the below function calls other files.
// First remove some columns that we will not use:
ds.DeleteColumn(8); // Car name
ds.DeleteColumn(7); // Car origin
ds.DeleteColumn(6); // Year
ds.DeleteUnknowns();
ds.NormalizeZScore(1);
ds.NormalizeZScore(2);
ds.NormalizeZScore(3);
ds.NormalizeZScore(4);
ds.NormalizeZScore(5);
var trainingData = ds.ExtractSupervised(1, 4, 0, 1);
var splitList = DataUtil.Split(trainingData, 0.75);
trainingData = splitList[0];
var validationData = splitList[1];
Console.WriteLine("Size of dataset: " + ds.Count);
Console.WriteLine("Size of training set: " + trainingData.Count);
Console.WriteLine("Size of validation set: " + validationData.Count);
var inputCount = trainingData[0].Input.Length;
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, inputCount));
network.AddLayer(new BasicLayer(new ActivationReLU(), true, 50));
network.AddLayer(new BasicLayer(new ActivationReLU(), true, 25));
network.AddLayer(new BasicLayer(new ActivationReLU(), true, 5));
network.AddLayer(new BasicLayer(new ActivationLinear(), false, 1));
network.FinalizeStructure();
network.Reset();
var train = new BackPropagation(network, trainingData, 0.000001, 0.9);
PerformIterationsEarlyStop(train, network, validationData, 20, new ErrorCalculationMSE());
Query(network, validationData);
}
public static void Run()
{
FileInfo networkFile = new FileInfo(@"D:\Imagery\network\network.eg");
var network = new BasicNetwork();
network.AddLayer(new BasicLayer(null, true, SIZE * SIZE * 3));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), true, NERUONCOUNT));
network.AddLayer(new BasicLayer(new ActivationSigmoid(), false, 2));
network.Structure.FinalizeStructure();
network.Reset();
if (System.IO.File.Exists(@"D:\Imagery\network\network.eg"))
{
network = (BasicNetwork)(Encog.Persist.EncogDirectoryPersistence.LoadObject(networkFile));
}
Encog.ML.Data.Image.ImageMLDataSet trainingSet = new Encog.ML.Data.Image.ImageMLDataSet(new RGBDownsample(), false, 1, -1);
Random rnd = new Random();
//take 1000,, take 5000 from nothing and scramble them
List <string> fileEntries = Directory.GetFiles(@"D:\Imagery\_Vege").OrderBy(x => rnd.Next()).Take(1000).ToList();
fileEntries.AddRange(Directory.GetFiles(@"D:\Imagery\_Nothing").OrderBy(x => rnd.Next()).Take(5000).ToArray());
fileEntries = fileEntries.OrderBy(x => rnd.Next()).Take(6000).ToList();
foreach (var file in fileEntries)
{
var bitmap = new System.Drawing.Bitmap(file);
ImageMLData data = new ImageMLData(bitmap);
if (file.Contains("_Nothing"))
{
BasicMLData ideal = new BasicMLData(Nothing);
trainingSet.Add(data, ideal);
}
else
{
BasicMLData ideal = new BasicMLData(Vegetation);
trainingSet.Add(data, ideal);
}
}
trainingSet.Downsample(SIZE, SIZE);
IMLTrain train = new Backpropagation(network, trainingSet, .001, 0.02)
{
};
int epoch = 1;
do
{
train.Iteration();
Console.WriteLine(@"Epoch #" + epoch + @" Error: " + train.Error);
epoch++;
} while (epoch < 50);
train.FinishTraining();
Encog.Persist.EncogDirectoryPersistence.SaveObject(networkFile, (BasicNetwork)network);
Encog.ML.Data.Image.ImageMLDataSet testingSet = new Encog.ML.Data.Image.ImageMLDataSet(new RGBDownsample(), false, 1, -1);
fileEntries = Directory.GetFiles(@"D:\Imagery\_VegeTest").ToList();
foreach (var file in fileEntries)
{
ImageMLData data = new ImageMLData(new System.Drawing.Bitmap(file));
BasicMLData ideal = new BasicMLData(Vegetation);
testingSet.Add(data, ideal);
}
fileEntries = Directory.GetFiles(@"D:\Imagery\_NothingTest").ToList();
foreach (var file in fileEntries)
{
ImageMLData data = new ImageMLData(new System.Drawing.Bitmap(file));
BasicMLData ideal = new BasicMLData(Nothing);
testingSet.Add(data, ideal);
}
testingSet.Downsample(SIZE, SIZE);
Console.WriteLine(@"Neural Network Results:");
foreach (IMLDataPair pair in testingSet)
{
IMLData output = network.Compute(pair.Input);
Console.WriteLine(@", actual (" + output[0] + @"," + output[1] + @"),ideal (" + pair.Ideal[0] + @"," + pair.Ideal[1] + ")");
}
EncogFramework.Instance.Shutdown();
}
/// <summary>
/// Generate the RSOM network.
/// </summary>
/// <returns>The neural network.</returns>
public BasicNetwork Generate()
{
ILayer output = new BasicLayer(new ActivationLinear(), false,
this.outputNeurons);
ILayer input = new BasicLayer(new ActivationLinear(), false,
this.inputNeurons);
BasicNetwork network = new BasicNetwork();
ILayer context = new ContextLayer(this.outputNeurons);
network.AddLayer(input);
network.AddLayer(output);
output.AddNext(context, SynapseType.OneToOne);
context.AddNext(input);
int y = PatternConst.START_Y;
input.X = PatternConst.START_X;
input.Y = y;
context.X = PatternConst.INDENT_X;
context.Y = y;
y += PatternConst.INC_Y;
output.X = PatternConst.START_X;
output.Y = y;
network.Structure.FinalizeStructure();
network.Reset();
return network;
}
static void Main(string[] args)
{
/// LIGHT DIODE ARRAY INFO
double[][] dataIn =
{
new double[3]
{
0, 0.5, 0.75
}
};
/// ACTUAL VOLUME
double[][] dataOut =
{
new double[1]
{
0
}
};
/// SETUP: MAKE PUBLIC
IMLDataSet mLDataSet = new BasicNeuralDataSet(dataIn, dataOut);
IMLDataSet mLInput;
IMLTrain mLTrain;
BasicNetwork basicNetwork = new BasicNetwork();
/// NEURAL NETWORK 3 > 5 > 5 > 5 > 1
basicNetwork.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 3));
basicNetwork.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 5));
basicNetwork.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 5));
basicNetwork.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 5));
basicNetwork.AddLayer(new BasicLayer(new ActivationSigmoid(), true, 1));
basicNetwork.Structure.FinalizeStructure();
basicNetwork.Reset();
mLTrain = new Backpropagation(basicNetwork, mLDataSet);
/// TRAINING
float numEpochs = 100;
for (float i = 0; i <= numEpochs; i++)
{
/// PROGRESSBAR
Console.Clear();
for (int pi = 0; pi <= (i / numEpochs) * 50; pi++)
{
Console.Write("-");
}
Console.WriteLine("> {0}%", (float)((i / numEpochs) * 100), numEpochs);
/// ITERATION
mLTrain.Iteration();
}
/// INPUT
while (true)
{
var in1 = Console.ReadLine();
var in2 = Console.ReadLine();
var in3 = Console.ReadLine();
double[][] inputIn =
{
new double[3]
{
double.Parse(in1), double.Parse(in2), double.Parse(in3)
}
};
mLInput = new BasicNeuralDataSet(inputIn, dataOut);
IMLData output = basicNetwork.Compute(mLInput[0].Input);
Console.WriteLine((float)output[0]);
}
}
public LotteryModel ByMachineLearningExecute()
{
try
{
if (this.lotteryRule.LotteryType != Enums.LotteryType.TheFiveNumberDraw)
{
return(null); //TODO: Make this for 6 and custom lottery draw
}
LotteryModel lm = new LotteryModel(lotteryRule);
var dbl = new List <LotteryResult>();
foreach (LotteryModel lotteryModel in this.lotteryCollection)
{
var res = new LotteryResult(
lotteryModel.Numbers[0],
lotteryModel.Numbers[1],
lotteryModel.Numbers[2],
lotteryModel.Numbers[3],
lotteryModel.Numbers[4]
);
dbl.Add(res);
}
dbl.Reverse();
var deep = 20;
var network = new BasicNetwork();
network.AddLayer(
new BasicLayer(null, true, 5 * deep));
network.AddLayer(
new BasicLayer(
new ActivationSigmoid(), true, 4 * 5 * deep));
network.AddLayer(
new BasicLayer(
new ActivationSigmoid(), true, 4 * 5 * deep));
network.AddLayer(
new BasicLayer(
new ActivationLinear(), true, 5));
network.Structure.FinalizeStructure();
var learningInput = new double[deep][];
for (int i = 0; i < deep; ++i)
{
learningInput[i] = new double[deep * 5];
for (int j = 0, k = 0; j < deep; ++j)
{
var idx = 2 * deep - i - j;
LotteryResult data = dbl[idx];
learningInput[i][k++] = (double)data.V1;
learningInput[i][k++] = (double)data.V2;
learningInput[i][k++] = (double)data.V3;
learningInput[i][k++] = (double)data.V4;
learningInput[i][k++] = (double)data.V5;
}
}
var learningOutput = new double[deep][];
for (int i = 0; i < deep; ++i)
{
var idx = deep - 1 - i;
var data = dbl[idx];
learningOutput[i] = new double[5]
{
(double)data.V1,
(double)data.V2,
(double)data.V3,
(double)data.V4,
(double)data.V5
};
}
var trainingSet = new BasicMLDataSet(
learningInput,
learningOutput);
var train = new ResilientPropagation(
network, trainingSet);
train.NumThreads = Environment.ProcessorCount;
START:
network.Reset();
RETRY:
var step = 0;
do
{
train.Iteration();
Console.WriteLine("Train Error: {0}", train.Error);
++step;
}while (train.Error > 0.001 && step < 20);
var passedCount = 0;
for (var i = 0; i < deep; ++i)
{
var should =
new LotteryResult(learningOutput[i]);
var inputn = new BasicMLData(5 * deep);
Array.Copy(
learningInput[i],
inputn.Data,
inputn.Data.Length);
var comput =
new LotteryResult(
((BasicMLData)network.
Compute(inputn)).Data);
var passed = should.ToString() == comput.ToString();
if (passed)
{
Console.ForegroundColor = ConsoleColor.Green;
++passedCount;
}
}
var input = new BasicMLData(5 * deep);
for (int i = 0, k = 0; i < deep; ++i)
{
var idx = deep - 1 - i;
var data = dbl[idx];
input.Data[k++] = (double)data.V1;
input.Data[k++] = (double)data.V2;
input.Data[k++] = (double)data.V3;
input.Data[k++] = (double)data.V4;
input.Data[k++] = (double)data.V5;
}
var perfect = dbl[0];
LotteryResult predict = new LotteryResult(
((BasicMLData)network.Compute(input)).Data);
Console.WriteLine("Predict: {0}", predict);
if (predict.IsOut())
{
goto START;
}
var t = passedCount < (deep * (double)9 / (double)10);
var isvalid = predict.IsValid();
if (t ||
!isvalid)
{
goto RETRY;
}
lm.AddNumber(predict.V1);
lm.AddNumber(predict.V2);
lm.AddNumber(predict.V3);
lm.AddNumber(predict.V4);
lm.AddNumber(predict.V5);
return(lm);
}
catch (Exception exception)
{
Console.WriteLine(exception.ToString());
return(null);
}
}
