public static HiddenMarkovClassifier<NormalDistribution> CreateModel1()
{
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a univariate sequence and the same sequence backwards.
double[][] sequences = new double[][]
{
new double[] { 0,1,2,3,4 }, // This is the first sequence with label = 0
new double[] { 4,3,2,1,0 }, // This is the second sequence with label = 1
};
// Labels for the sequences
int[] labels = { 0, 1 };
// Creates a sequence classifier containing 2 hidden Markov Models
// with 2 states and an underlying Normal distribution as density.
NormalDistribution density = new NormalDistribution();
var classifier = new HiddenMarkovClassifier<NormalDistribution>(2, new Ergodic(2), density);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning<NormalDistribution>(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning<NormalDistribution>(classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences, labels);
return classifier;
}
public int Recognize(ISoundSignalReader signal, HiddenMarkovClassifier hmm, out string name,
SignalVisitor voiceVisitor = null)
{
var featureUtility = new FeatureUtility(_engineParameters);
signal.Reset();
var features = featureUtility.ExtractFeatures(signal, voiceVisitor).First();
var observations = _codeBook.Quantize(features.Select(item => new Point(item)).ToArray());
double[] responsabilities;
var ret = hmm.Compute(observations, out responsabilities);
var models = hmm.Models;
var likelyHoodValue = Double.MinValue;
name = string.Empty;
foreach (var model in models)
{
var val = model.Evaluate(observations);
if (val > likelyHoodValue)
{
likelyHoodValue = val;
name = model.Tag.ToString();
}
}
return ret;
}
/// <summary>
/// Creates the ensemble
/// </summary>
private void btnCreate_Click(object sender, EventArgs e)
{
DataTable source = dgvSequenceSource.DataSource as DataTable;
if (source == null)
{
MessageBox.Show("Please load some data by clicking 'Open' under the 'File' menu first. " +
"A sample dataset can be found in the folder 'Resources' contained in the same " +
"directory as this application.");
return;
}
DataTable k = source.DefaultView.ToTable(true, "Label", "States");
// Get the number of different classes in the data
int classes = k.Rows.Count;
string[] categories = new string[classes];
int[] states = new int[classes];
for (int i = 0; i < classes; i++)
{
// Gets the label name
categories[i] = k.Rows[i]["Label"] as string;
// Gets the number of states to recognize each label
states[i] = int.Parse(k.Rows[i]["States"] as string);
}
hmmc = new HiddenMarkovClassifier(classes, states, 3, categories);
dgvModels.DataSource = hmmc.Models;
}
public void LearnTest()
{
// Declare some testing data
int[][] inputs = new int[][]
{
new int[] { 0,1,1,0 }, // Class 0
new int[] { 0,0,1,0 }, // Class 0
new int[] { 0,1,1,1,0 }, // Class 0
new int[] { 0,1,0 }, // Class 0
new int[] { 1,0,0,1 }, // Class 1
new int[] { 1,1,0,1 }, // Class 1
new int[] { 1,0,0,0,1 }, // Class 1
new int[] { 1,0,1 }, // Class 1
};
int[] outputs = new int[]
{
0,0,0,0, // First four sequences are of class 0
1,1,1,1, // Last four sequences are of class 1
};
// We are trying to predict two different classes
int classes = 2;
// Each sequence may have up to two symbols (0 or 1)
int symbols = 2;
// Nested models will have two states each
int[] states = new int[] { 2, 2 };
// Creates a new Hidden Markov Model Classifier with the given parameters
HiddenMarkovClassifier classifier = new HiddenMarkovClassifier(classes, states, symbols);
// Create a new learning algorithm to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning(classifier.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 0
}
);
// Train the sequence classifier using the algorithm
double likelihood = teacher.Run(inputs, outputs);
// Will assert the models have learned the sequences correctly.
for (int i = 0; i < inputs.Length; i++)
{
int expected = outputs[i];
int actual = classifier.Compute(inputs[i], out likelihood);
Assert.AreEqual(expected, actual);
}
}
public void LearnTest1()
{
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a univariate sequence and the same sequence backwards.
double[][] sequences = new double[][]
{
new double[] { 0,1,2,3,4 }, // This is the first sequence with label = 0
new double[] { 4,3,2,1,0 }, // This is the second sequence with label = 1
};
// Labels for the sequences
int[] labels = { 0, 1 };
// Creates a sequence classifier containing 2 hidden Markov Models
// with 2 states and an underlying Normal distribution as density.
NormalDistribution density = new NormalDistribution();
var classifier = new HiddenMarkovClassifier<NormalDistribution>(2, new Ergodic(2), density);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning<NormalDistribution>(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning<NormalDistribution>(classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences, labels);
// Calculate the probability that the given
// sequences originated from the model
double likelihood1, likelihood2;
// Try to classify the first sequence (output should be 0)
int c1 = classifier.Compute(sequences[0], out likelihood1);
// Try to classify the second sequence (output should be 1)
int c2 = classifier.Compute(sequences[1], out likelihood2);
Assert.AreEqual(0, c1);
Assert.AreEqual(1, c2);
Assert.AreEqual(-13.271981026832929, logLikelihood, 1e-10);
Assert.AreEqual(0.99999791320102149, likelihood1, 1e-10);
Assert.AreEqual(0.99999791320102149, likelihood2, 1e-10);
Assert.IsFalse(double.IsNaN(logLikelihood));
Assert.IsFalse(double.IsNaN(likelihood1));
Assert.IsFalse(double.IsNaN(likelihood2));
}
public static HiddenMarkovClassifier<Independent> CreateModel1()
{
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a multivariate sequence and the same sequence backwards.
double[][][] sequences = new double[][][]
{
new double[][]
{
// This is the first sequence with label = 0
new double[] { 0 },
new double[] { 1 },
new double[] { 2 },
new double[] { 3 },
new double[] { 4 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 4 },
new double[] { 3 },
new double[] { 2 },
new double[] { 1 },
new double[] { 0 },
}
};
// Labels for the sequences
int[] labels = { 0, 1 };
// Creates a sequence classifier containing 2 hidden Markov Models
// with 2 states and an underlying Normal distribution as density.
NormalDistribution component = new NormalDistribution();
Independent density = new Independent(component);
var classifier = new HiddenMarkovClassifier<Independent>(2, new Ergodic(2), density);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning<Independent>(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning<Independent>(classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences, labels);
Assert.AreEqual(-13.271981026832929d, logLikelihood);
return classifier;
}
public static HiddenMarkovClassifier CreateModel1()
{
// Declare some testing data
int[][] inputs = new int[][]
{
new int[] { 0,1,1,0 }, // Class 0
new int[] { 0,0,1,0 }, // Class 0
new int[] { 0,1,1,1,0 }, // Class 0
new int[] { 0,1,0 }, // Class 0
new int[] { 1,0,0,1 }, // Class 1
new int[] { 1,1,0,1 }, // Class 1
new int[] { 1,0,0,0,1 }, // Class 1
new int[] { 1,0,1 }, // Class 1
};
int[] outputs = new int[]
{
0,0,0,0, // First four sequences are of class 0
1,1,1,1, // Last four sequences are of class 1
};
// We are trying to predict two different classes
int classes = 2;
// Each sequence may have up to two symbols (0 or 1)
int symbols = 2;
// Nested models will have two states each
int[] states = new int[] { 2, 2 };
// Creates a new Hidden Markov Model Classifier with the given parameters
HiddenMarkovClassifier classifier = new HiddenMarkovClassifier(classes, states, symbols);
// Create a new learning algorithm to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning(classifier.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 0
}
);
// Train the sequence classifier using the algorithm
double likelihood = teacher.Run(inputs, outputs);
return classifier;
}
public static void LearnAndPredictContinuous()
{
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a univariate sequence and the same sequence backwards.
double[][] sequences = new double[][]
{
new double[] { 0, 1, 2, 3, 4 }, // This is the first sequence with label = 0
new double[] { 4, 3, 2, 1, 0 }, // This is the second sequence with label = 1
};
// Labels for the sequences
int[] labels = { 0, 1 };
// Creates a new Continuous-density Hidden Markov Model Sequence Classifier
// containing 2 hidden Markov Models with 2 states and an underlying Normal
// distribution as the continuous probability density.
Gaussian density = new Gaussian();
var classifier = new HiddenMarkovClassifier(2, new Ergodic(2), density);
// Create a new learning algorithm to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning(classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0
}
);
// Train the sequence classifier using the algorithm
teacher.Run(sequences, labels);
// Calculate the probability that the given
// sequences originated from the model
double likelihood;
// Try to classify the first sequence (output should be 0)
int c1 = classifier.Compute(sequences[0], out likelihood);
Console.WriteLine("c1: {0}", c1);
// Try to classify the second sequence (output should be 1)
int c2 = classifier.Compute(sequences[1], out likelihood);
Console.WriteLine("c2: {0}", c2);
}
public void HiddenMarkovHiddenPotentialFunctionConstructorTest()
{
HiddenMarkovClassifier <NormalDistribution> model = CreateModel1();
var target = new MarkovContinuousFunction(model);
var features = target.Features;
double[] weights = target.Weights;
Assert.AreEqual(26, features.Length);
Assert.AreEqual(26, weights.Length);
int k = 0;
for (int c = 0; c < model.Classes; c++)
{
Assert.AreEqual(Math.Log(model.Priors[c]), weights[k++]);
for (int i = 0; i < model[c].States; i++)
{
Assert.AreEqual(model[c].Probabilities[i], weights[k++]);
}
for (int i = 0; i < model[c].States; i++)
{
for (int j = 0; j < model[c].States; j++)
{
Assert.AreEqual(model[c].Transitions[i, j], weights[k++]);
}
}
for (int i = 0; i < model[c].States; i++)
{
for (int j = 0; j < model[c].Dimension; j++)
{
double mean = model[c].Emissions[i].Mean;
double var = model[c].Emissions[i].Variance;
double l2ps = System.Math.Log(2 * System.Math.PI * var);
Assert.AreEqual(-0.5 * (l2ps + (mean * mean) / var), weights[k++]);
Assert.AreEqual(mean / var, weights[k++]);
Assert.AreEqual(-1.0 / (2 * var), weights[k++]);
}
}
}
}
/// <summary>
/// Creates a new <see cref="RunningMarkovClassifier"/>.
/// </summary>
///
/// <param name="model">The hidden Markov classifier model.</param>
///
public RunningMarkovClassifier(HiddenMarkovClassifier model)
{
this.Classifier = model;
this.Responses = new double[model.Classes];
this.models = new RunningMarkovStatistics[model.Classes];
for (int i = 0; i < model.Classes; i++)
{
this.models[i] = new RunningMarkovStatistics(model[i]);
}
if (model.Threshold != null)
{
this.threshold = new RunningMarkovStatistics(model.Threshold);
}
}
public void RunTest()
{
HiddenMarkovClassifier hmm = HiddenMarkovClassifierPotentialFunctionTest.CreateModel1();
var function = new MarkovDiscreteFunction(hmm);
var model = new HiddenConditionalRandomField <int>(function);
var target = new HiddenQuasiNewtonLearning <int>(model);
double[] actual = new double[inputs.Length];
double[] expected = new double[inputs.Length];
for (int i = 0; i < inputs.Length; i++)
{
actual[i] = model.Compute(inputs[i]);
expected[i] = outputs[i];
}
for (int i = 0; i < inputs.Length; i++)
{
Assert.AreEqual(expected[i], actual[i]);
}
double ll0 = model.LogLikelihood(inputs, outputs);
double error = target.Run(inputs, outputs);
double ll1 = model.LogLikelihood(inputs, outputs);
for (int i = 0; i < inputs.Length; i++)
{
actual[i] = model.Compute(inputs[i]);
expected[i] = outputs[i];
}
Assert.AreEqual(-0.00046872579976353634, ll0, 1e-10);
Assert.AreEqual(0.0, error, 1e-10);
Assert.AreEqual(error, -ll1);
Assert.IsFalse(Double.IsNaN(ll0));
Assert.IsFalse(Double.IsNaN(error));
for (int i = 0; i < inputs.Length; i++)
{
Assert.AreEqual(expected[i], actual[i]);
}
Assert.IsTrue(ll1 > ll0);
}
public HiddenMarkovClassifierLearning(HiddenMarkovClassifier classifier, HiddenMarkovModelLearningAlgorithmEntity algorithm = null)
{
mClassifier = classifier;
int class_count = classifier.ClassCount;
mAlgorithmEntity = algorithm;
if (mAlgorithmEntity == null)
{
mAlgorithmEntity = model_index => new BaumWelchLearning(classifier.Models[model_index])
{
Tolerance = 0.001,
Iterations = 0
};
}
}
public void ForwardTest2()
{
HiddenMarkovClassifier <Independent> hmm = IndependentMarkovClassifierPotentialFunctionTest
.CreateModel3();
var function = new MarkovMultivariateFunction(hmm, includePriors: false);
double[][][] observations = IndependentMarkovClassifierPotentialFunctionTest.sequences2;
int[] labels = IndependentMarkovClassifierPotentialFunctionTest.labels2;
foreach (double[][] x in observations)
{
foreach (int y in labels)
{
double[] scaling1;
double logLikelihood1;
double[,] actual = Accord.Statistics.Models.Fields.
ForwardBackwardAlgorithm.Forward(function.Factors[y], x, y, out scaling1, out logLikelihood1);
double[] scaling2;
double logLikelihood2;
double[,] expected = Accord.Statistics.Models.Markov.
ForwardBackwardAlgorithm.Forward(hmm.Models[y], x, out scaling2, out logLikelihood2);
for (int i = 0; i < actual.GetLength(0); i++)
{
for (int j = 0; j < actual.GetLength(1); j++)
{
Assert.AreEqual(expected[i, j], actual[i, j], 1e-10);
Assert.IsFalse(Double.IsNaN(actual[i, j]));
}
}
Assert.AreEqual(logLikelihood1, logLikelihood2, 1e-10);
for (int i = 0; i < scaling1.Length; i++)
{
Assert.AreEqual(scaling1[i], scaling2[i], 1e-8);
Assert.IsFalse(Double.IsNaN(scaling1[i]));
Assert.IsFalse(Double.IsNaN(scaling2[i]));
}
}
}
}
public void TrainModel(int states = 5, int iterations = 0, double tolerance = 0.01, bool rejection = false)
{
var samples = DataStore.Samples;
var labels = DataStore.Labels;
double[][][] inputs = new double[samples.Count][][];
int[] outputs = new int[samples.Count];
for (int i = 0; i < inputs.Length; i++)
{
inputs[i] = samples[i].Input;
outputs[i] = samples[i].Output;
}
_hmm = new HiddenMarkovClassifier <NormalDistribution, double>(labels.Count,
new Forward(states), new NormalDistribution(2), labels.ToArray());
// Create the learning algorithm for the ensemble classifier
var teacher = new HiddenMarkovClassifierLearning <NormalDistribution, double>(_hmm)
{
// Train each model until the log-likelihood changes less than 0.001
Learner = modelIndex => new BaumWelchLearning <NormalDistribution, double>(_hmm.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0
}
};
teacher.Empirical = true;
teacher.Rejection = rejection;
// Run the learning algorithm
// double error = teacher.Learn(inputs, outputs);
// Classify all training instances
foreach (var sample in samples)
{
// sample.RecognizedAs = _hmm.Compute(sample.Input);
}
}
public void Aprender(IDadosSinaisDinamicos dados)
{
var quantidadeCaracteristicas = dados.CaracteristicasSinais[0][0].Length;
hmm = new HiddenMarkovClassifier<MultivariateNormalDistribution>(
classes: dados.QuantidadeClasses,
topology: new Forward(QuantidadeEstados),
initial: new MultivariateNormalDistribution(quantidadeCaracteristicas)
);
var teacher = new HiddenMarkovClassifierLearning<MultivariateNormalDistribution>(hmm,
modelIndex => new BaumWelchLearning<MultivariateNormalDistribution>(hmm.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 100,
FittingOptions = new NormalOptions { Regularization = 1e-5}
});
teacher.Run(dados.CaracteristicasSinais, dados.IdentificadoresSinais);
}
public void ComputeTest()
{
HiddenMarkovClassifier model = CreateModel1();
MarkovDiscreteFunction target = new MarkovDiscreteFunction(model);
double actual;
double expected;
int[] x = { 0, 1 };
for (int c = 0; c < model.Classes; c++)
{
for (int i = 0; i < model[c].States; i++)
{
// Check initial state transitions
double xa = model.Priors[c];
double xb = Math.Exp(model[c].Probabilities[i]);
double xc = Math.Exp(model[c].Emissions[i, x[0]]);
expected = xa * xb * xc;
actual = Math.Exp(target.Factors[c].Compute(-1, i, x, 0, c));
Assert.AreEqual(expected, actual, 1e-6);
Assert.IsFalse(double.IsNaN(actual));
}
for (int t = 1; t < x.Length; t++)
{
// Check normal state transitions
for (int i = 0; i < model[c].States; i++)
{
for (int j = 0; j < model[c].States; j++)
{
double xb = Math.Exp(model[c].Transitions[i, j]);
double xc = Math.Exp(model[c].Emissions[j, x[t]]);
expected = xb * xc;
actual = Math.Exp(target.Factors[c].Compute(i, j, x, t, c));
Assert.AreEqual(expected, actual, 1e-6);
Assert.IsFalse(double.IsNaN(actual));
}
}
}
}
}
public void ComputeTest4()
{
int[] labels;
double[][][] words;
HiddenMarkovClassifier <Independent <NormalDistribution> > model =
CreateModel4(out words, out labels, false);
var target = new MarkovMultivariateFunction(model);
var hcrf = new HiddenConditionalRandomField <double[]>(target);
Assert.AreEqual(3, model.Priors.Length);
Assert.AreEqual(1 / 3.0, model.Priors[0]);
Assert.AreEqual(1 / 3.0, model.Priors[1]);
Assert.AreEqual(1 / 3.0, model.Priors[2]);
check4(words, model, target, hcrf);
}
public void GradientTest_MarkovMultivariate()
{
// Creates a sequence classifier containing 2 hidden Markov Models
// with 2 states and an underlying Normal distribution as density.
MultivariateNormalDistribution density = new MultivariateNormalDistribution(3);
var hmm = new HiddenMarkovClassifier <MultivariateNormalDistribution>(2, new Ergodic(2), density);
double[][][] inputs =
{
new [] { new double[] { 0, 1, 0 }, new double[] { 0, 1, 0 }, new double[] { 0, 1, 0 } },
new [] { new double[] { 1, 6, 2 }, new double[] { 2, 1, 6 }, new double[] { 1, 1, 0 } },
new [] { new double[] { 9, 1, 0 }, new double[] { 0, 1, 5 }, new double[] { 0, 0, 0 } },
};
int[] outputs =
{
0, 0, 1
};
var function = new MarkovMultivariateFunction(hmm);
var model = new HiddenConditionalRandomField <double[]>(function);
var target = new ForwardBackwardGradient <double[]>(model);
FiniteDifferences diff = new FiniteDifferences(function.Weights.Length)
{
StepSize = 1e-5
};
diff.Function = parameters => func(model, parameters, inputs, outputs);
double[] expected = diff.Compute(function.Weights);
double[] actual = target.Gradient(function.Weights, inputs, outputs);
for (int i = 0; i < actual.Length; i++)
{
Assert.AreEqual(expected[i], actual[i], 0.05);
Assert.IsFalse(double.IsNaN(actual[i]));
Assert.IsFalse(double.IsNaN(expected[i]));
}
}
private void LoadFromHMMFile_Click(object sender, EventArgs e)
{
OpenFileDialog dlg = new OpenFileDialog();
dlg.Filter = "Gestures (*.hmm)|*.hmm";
dlg.Title = "Load Gestures";
dlg.RestoreDirectory = false;
dlg.Multiselect = true;
if (dlg.ShowDialog(this) == DialogResult.OK)
{
_hmmc = HiddenMarkovClassifier.Load(dlg.FileName);
_hmms = _hmmc.Models;
if (_hmmc != null)
{
lblResult.Text = "Success!!";
}
ReloadViewForm();
}
}
public void LogForwardTest3()
{
MultivariateNormalDistribution density = new MultivariateNormalDistribution(3);
var hmm = new HiddenMarkovClassifier <MultivariateNormalDistribution>(2, new Ergodic(2), density);
double[][][] inputs =
{
new [] { new double[] { 0, 1, 0 }, new double[] { 0, 1, 0 }, new double[] { 0, 1, 0 } },
new [] { new double[] { 1, 6, 2 }, new double[] { 2, 1, 6 }, new double[] { 1, 1, 0 } },
new [] { new double[] { 9, 1, 0 }, new double[] { 0, 1, 5 }, new double[] { 0, 0, 0 } },
};
int[] outputs =
{
0, 0, 1
};
var function = new MarkovMultivariateFunction(hmm);
var observations = inputs[0];
double[,] expected = Matrix.Log(Accord.Statistics.Models.Fields.
ForwardBackwardAlgorithm.Forward(function.Factors[0], observations, 0));
double logLikelihood;
double[,] actual = Accord.Statistics.Models.Fields.
ForwardBackwardAlgorithm.LogForward(function.Factors[0], observations, 0, out logLikelihood);
Assert.IsTrue(expected.IsEqual(actual, 1e-10));
double p = 0;
for (int i = 0; i < hmm[0].States; i++)
{
p += Math.Exp(actual[observations.Length - 1, i]);
}
Assert.AreEqual(Math.Exp(logLikelihood), p, 1e-8);
Assert.IsFalse(double.IsNaN(p));
}
public void HiddenMarkovHiddenPotentialFunctionConstructorTest()
{
HiddenMarkovClassifier model = CreateModel1();
MarkovDiscreteFunction target = new MarkovDiscreteFunction(model);
var features = target.Features;
double[] weights = target.Weights;
Assert.AreEqual(22, features.Length);
Assert.AreEqual(22, weights.Length);
int k = 0;
for (int c = 0; c < model.Classes; c++)
{
Assert.AreEqual(Math.Log(model.Priors[c]), weights[k++]);
for (int i = 0; i < model[c].States; i++)
{
Assert.AreEqual(model[c].Probabilities[i], weights[k++]);
}
for (int i = 0; i < model[c].States; i++)
{
for (int j = 0; j < model[c].States; j++)
{
Assert.AreEqual(model[c].Transitions[i, j], weights[k++]);
}
}
for (int i = 0; i < model[c].States; i++)
{
for (int j = 0; j < model.Symbols; j++)
{
Assert.AreEqual(model[c].Emissions[i, j], weights[k++]);
}
}
}
}
private void button1_Click(object sender, EventArgs e)
{
var classes = 4;
var states = new[] { 1, 2, 2, 3 };
var cat = new[] { "ខ្ញុំ", "ទៅ", "ខ្លួន", "ក" };
//var cat = new[] { "A", "B" };
_hmmc = new HiddenMarkovClassifier(classes, states, 4, cat);
// Train the ensemble
var sequences = new[]
{
new[] { 1, 1, 1 },
new[] { 0, 2 },
new[] { 0, 1, 2 },
new[] { 1, 2 }
};
var labels = new[] { 0, 1, 2, 3 };
var teacher = new HiddenMarkovClassifierLearning(_hmmc, i =>
new BaumWelchLearning(_hmmc.Models[i])
{
Iterations = 0,
Tolerance = 0.0001
}
);
teacher.Run(sequences, labels);
var m = _hmmc.Models;
var test = new[] { 1, 2 };
double likelihood;
var label = _hmmc.Compute(test, out likelihood);
MessageBox.Show(_hmmc.Models[label].Tag.ToString() + " P =" + likelihood);
}
public void GradientTest2()
{
HiddenMarkovClassifier hmm = HiddenMarkovClassifierPotentialFunctionTest.CreateModel1();
var function = new MarkovDiscreteFunction(hmm);
var model = new HiddenConditionalRandomField <int>(function);
var target = new ForwardBackwardGradient <int>(model);
FiniteDifferences diff = new FiniteDifferences(function.Weights.Length);
diff.Function = parameters => func(model, parameters);
double[] expected = diff.Compute(function.Weights);
double[] actual = target.Gradient(function.Weights, inputs, outputs);
for (int i = 0; i < actual.Length; i++)
{
Assert.AreEqual(expected[i], actual[i], 1e-5);
Assert.IsFalse(double.IsNaN(actual[i]));
Assert.IsFalse(double.IsNaN(expected[i]));
}
}
private void button1_Click(object sender, EventArgs e)
{
var classes = 4;
var states = new[]{1,2,2,3};
var cat = new[] {"ខ្ញុំ", "ទៅ", "ខ្លួន", "ក"};
//var cat = new[] { "A", "B" };
_hmmc = new HiddenMarkovClassifier(classes, states, 4, cat);
// Train the ensemble
var sequences = new[]
{
new[] {1, 1, 1},
new[] {0, 2},
new[] {0, 1, 2},
new[] {1, 2}
};
var labels = new[] {0, 1, 2, 3};
var teacher = new HiddenMarkovClassifierLearning(_hmmc, i =>
new BaumWelchLearning(_hmmc.Models[i])
{
Iterations = 0,
Tolerance = 0.0001
}
);
teacher.Run(sequences, labels);
var m = _hmmc.Models;
var test = new[]{1,2};
double likelihood;
var label = _hmmc.Compute(test, out likelihood);
MessageBox.Show(_hmmc.Models[label].Tag.ToString()+ " P =" + likelihood);
}
public static HiddenMarkovClassifier<Independent> CreateModel3(out double[][][] sequences2, out int[] labels2)
{
sequences2 = new double[][][]
{
new double[][]
{
// This is the first sequence with label = 0
new double[] { 1, 1.12, 2.41, 1.17, 9.3 },
new double[] { 1, 2.54, 1.45, 0.16, 4.5 },
new double[] { 1, 3.46, 2.63, 1.15, 9.2 },
new double[] { 1, 4.73, 0.41, 1.54, 5.5 },
new double[] { 2, 5.81, 2.42, 1.13, 9.1 },
},
new double[][]
{
// This is the first sequence with label = 0
new double[] { 0, 1.49, 2.48, 1.18, 9.37 },
new double[] { 1, 2.18, 1.44, 2.19, 1.56 },
new double[] { 1, 3.77, 2.62, 1.10, 9.25 },
new double[] { 2, 4.76, 5.44, 3.58, 5.54 },
new double[] { 2, 5.85, 2.46, 1.16, 5.13 },
new double[] { 2, 4.84, 5.44, 3.54, 5.52 },
new double[] { 2, 5.83, 3.41, 1.22, 5.11 },
},
new double[][]
{
// This is the first sequence with label = 0
new double[] { 2, 1.11, 2.41, 1.12, 2.31 },
new double[] { 1, 2.52, 3.73, 0.12, 4.50 },
new double[] { 1, 3.43, 2.61, 1.24, 9.29 },
new double[] { 1, 4.74, 2.42, 2.55, 6.57 },
new double[] { 2, 5.85, 2.43, 1.16, 9.16 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 0, 1.26, 5.44, 1.56, 9.55 },
new double[] { 2, 2.67, 5.45, 4.27, 1.54 },
new double[] { 1, 1.28, 3.46, 2.18, 4.13 },
new double[] { 1, 5.89, 2.57, 1.79, 5.02 },
new double[] { 0, 1.40, 2.48, 2.10, 6.41 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 2, 3.21, 2.49, 1.54, 9.17 },
new double[] { 2, 2.62, 5.40, 4.25, 1.54 },
new double[] { 1, 1.53, 6.49, 2.17, 4.52 },
new double[] { 1, 2.84, 2.58, 1.73, 6.04 },
new double[] { 1, 1.45, 2.47, 2.28, 5.42 },
new double[] { 1, 1.46, 2.46, 2.35, 5.41 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 1, 5.27, 5.45, 1.4, 9.5 },
new double[] { 2, 2.68, 2.54, 3.2, 2.2 },
new double[] { 1, 2.89, 3.83, 2.6, 4.1 },
new double[] { 1, 1.80, 1.32, 1.2, 4.2 },
new double[] { 0, 1.41, 2.41, 2.1, 6.4 },
}
};
labels2 = new[] { 0, 0, 0, 1, 1, 1 };
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a multivariate sequence and the same sequence backwards.
var comp1 = new GeneralDiscreteDistribution(3);
var comp2 = new NormalDistribution(1);
var comp3 = new NormalDistribution(2);
var comp4 = new NormalDistribution(3);
var comp5 = new NormalDistribution(4);
var density = new Independent(comp1, comp2, comp3, comp4, comp5);
// Creates a sequence classifier containing 2 hidden Markov Models with 2 states
// and an underlying multivariate mixture of Normal distributions as density.
var classifier = new HiddenMarkovClassifier<Independent>(
2, new Forward(5), density);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning<Independent>(
classifier,
// Train each model until the log-likelihood changes less than 0.0001
modelIndex => new BaumWelchLearning<Independent>(
classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0,
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences2, labels2);
return classifier;
}
private void btnLearnHMM_Click(object sender, EventArgs e)
{
if (gridSamples.Rows.Count == 0)
{
MessageBox.Show("Please load or insert some data first.");
return;
}
BindingList<Sequence> samples = database.Samples;
BindingList<String> classes = database.Classes;
double[][][] inputs = new double[samples.Count][][];
int[] outputs = new int[samples.Count];
for (int i = 0; i < inputs.Length; i++)
{
inputs[i] = samples[i].Input;
outputs[i] = samples[i].Output;
}
int states = 5;
int iterations = 0;
double tolerance = 0.01;
bool rejection = false;
hmm = new HiddenMarkovClassifier<MultivariateNormalDistribution>(classes.Count,
new Forward(states), new MultivariateNormalDistribution(2), classes.ToArray());
// Create the learning algorithm for the ensemble classifier
var teacher = new HiddenMarkovClassifierLearning<MultivariateNormalDistribution>(hmm,
// Train each model using the selected convergence criteria
i => new BaumWelchLearning<MultivariateNormalDistribution>(hmm.Models[i])
{
Tolerance = tolerance,
Iterations = iterations,
FittingOptions = new NormalOptions()
{
Regularization = 1e-5
}
}
);
teacher.Empirical = true;
teacher.Rejection = rejection;
// Run the learning algorithm
double error = teacher.Run(inputs, outputs);
// Classify all training instances
foreach (var sample in database.Samples)
{
sample.RecognizedAs = hmm.Compute(sample.Input);
}
foreach (DataGridViewRow row in gridSamples.Rows)
{
var sample = row.DataBoundItem as Sequence;
row.DefaultCellStyle.BackColor = (sample.RecognizedAs == sample.Output) ?
Color.LightGreen : Color.White;
}
btnLearnHCRF.Enabled = true;
}
/// <summary>
/// Creates a new instance of the learning algorithm for a given
/// Markov sequence classifier.
/// </summary>
///
public HiddenMarkovClassifierLearning(HiddenMarkovClassifier <TDistribution, TObservation> classifier)
: base(classifier)
{
}
private static void check4(double[][][] words, HiddenMarkovClassifier<Independent> model, MarkovMultivariateFunction target, HiddenConditionalRandomField<double[]> hcrf)
{
double actual;
double expected;
foreach (var x in words)
{
for (int c = 0; c < model.Classes; c++)
{
for (int i = 0; i < model[c].States; i++)
{
// Check initial state transitions
double xa = model.Priors[c];
double xb = Math.Exp(model[c].Probabilities[i]);
double xc = model[c].Emissions[i].ProbabilityDensityFunction(x[0]);
expected = xa * xb * xc;
actual = Math.Exp(target.Factors[c].Compute(-1, i, x, 0, c));
Assert.IsTrue(expected.IsRelativelyEqual(actual, 1e-10));
Assert.IsFalse(double.IsNaN(actual));
}
for (int t = 1; t < x.Length; t++)
{
// Check normal state transitions
for (int i = 0; i < model[c].States; i++)
{
for (int j = 0; j < model[c].States; j++)
{
double xb = Math.Exp(model[c].Transitions[i, j]);
double xc = model[c].Emissions[j].ProbabilityDensityFunction(x[t]);
expected = xb * xc;
actual = Math.Exp(target.Factors[c].Compute(i, j, x, t, c));
Assert.IsTrue(expected.IsRelativelyEqual(actual, 1e-10));
Assert.IsFalse(double.IsNaN(actual));
}
}
}
actual = Math.Exp(model.LogLikelihood(x, c));
expected = Math.Exp(hcrf.LogLikelihood(x, c));
Assert.AreEqual(expected, actual, 1e-10);
Assert.IsFalse(double.IsNaN(actual));
actual = model.Compute(x);
expected = hcrf.Compute(x);
Assert.AreEqual(expected, actual);
Assert.IsFalse(double.IsNaN(actual));
}
}
}
private void openDataDialog_FileOk(object sender, System.ComponentModel.CancelEventArgs e)
{
hmm = null;
hcrf = null;
using (var stream = openDataDialog.OpenFile())
database.Load(stream);
btnLearnHMM.Enabled = true;
btnLearnHCRF.Enabled = false;
panelClassification.Visible = false;
panelUserLabeling.Visible = false;
}
/// <summary>
/// Constructs a new potential function modeling Hidden Markov Models.
/// </summary>
///
/// <param name="classifier">The classifier model.</param>
/// <param name="includePriors">True to include class features (priors), false otherwise.</param>
///
public MarkovDiscreteFunction(HiddenMarkovClassifier <GeneralDiscreteDistribution, int> classifier, bool includePriors = true)
{
this.Symbols = classifier.Models[0].Emissions[0].Length;
this.Outputs = classifier.Classes;
int factorIndex = 0;
var factorParams = new List <double>();
var factorFeatures = new List <IFeature <int> >();
this.Factors = new FactorPotential <int> [Outputs];
int[] classOffset = new int[classifier.Classes];
int[] edgeOffset = new int[classifier.Classes];
int[] stateOffset = new int[classifier.Classes];
int[] classCount = new int[classifier.Classes];
int[] edgeCount = new int[classifier.Classes];
int[] stateCount = new int[classifier.Classes];
// Create features for initial class probabilities
for (int c = 0; c < classifier.Classes; c++)
{
var stateParams = new List <double>();
var stateFeatures = new List <IFeature <int> >();
var edgeParams = new List <double>();
var edgeFeatures = new List <IFeature <int> >();
var classParams = new List <double>();
var classFeatures = new List <IFeature <int> >();
var model = classifier[c];
if (includePriors)
{
// Create features for class labels
classParams.Add(Math.Log(classifier.Priors[c]));
classFeatures.Add(new OutputFeature <int>(this, c, c));
}
// Create features for initial state probabilities
for (int i = 0; i < model.States; i++)
{
edgeParams.Add(model.LogInitial[i]);
edgeFeatures.Add(new InitialFeature <int>(this, c, i));
}
// Create features for state transition probabilities
for (int i = 0; i < model.States; i++)
{
for (int j = 0; j < model.States; j++)
{
edgeParams.Add(model.LogTransitions[i][j]);
edgeFeatures.Add(new TransitionFeature <int>(this, c, i, j));
}
}
// Create features for symbol emission probabilities
for (int i = 0; i < model.States; i++)
{
for (int k = 0; k < model.Emissions[i].Length; k++)
{
stateParams.Add(model.Emissions[i][k]);
stateFeatures.Add(new EmissionFeature(this, c, i, k));
}
}
classOffset[c] = factorIndex;
edgeOffset[c] = factorIndex + classParams.Count;
stateOffset[c] = factorIndex + classParams.Count + edgeParams.Count;
classCount[c] = classParams.Count;
edgeCount[c] = edgeParams.Count;
stateCount[c] = stateParams.Count;
// 1. classes
factorFeatures.AddRange(classFeatures);
factorParams.AddRange(classParams);
// 2. edges
factorFeatures.AddRange(edgeFeatures);
factorParams.AddRange(edgeParams);
// 3. states
factorFeatures.AddRange(stateFeatures);
factorParams.AddRange(stateParams);
factorIndex += classParams.Count + stateParams.Count + edgeParams.Count;
}
Accord.Diagnostics.Debug.Assert(factorIndex == factorParams.Count);
Accord.Diagnostics.Debug.Assert(factorIndex == factorFeatures.Count);
this.Weights = factorParams.ToArray();
this.Features = factorFeatures.ToArray();
for (int c = 0; c < classifier.Models.Length; c++)
{
Factors[c] = new MarkovDiscreteFactor(this, classifier.Models[c].States, c, Symbols,
classIndex: classOffset[c], classCount: classCount[c], // 1. classes
edgeIndex: edgeOffset[c], edgeCount: edgeCount[c], // 2. edges
stateIndex: stateOffset[c], stateCount: stateCount[c]); // 3. states
}
}
/// <summary>
/// Constructs a new potential function modeling Hidden Markov Models.
/// </summary>
///
/// <param name="classifier">A hidden Markov sequence classifier.</param>
/// <param name="includePriors">True to include class features (priors), false otherwise.</param>
///
public MarkovMultivariateFunction(
HiddenMarkovClassifier <MultivariateNormalDistribution> classifier, bool includePriors = true)
{
this.Outputs = classifier.Classes;
this.Dimensions = classifier.Models[0].Dimension;
int factorIndex = 0;
var factorParams = new List <double>();
var factorFeatures = new List <IFeature <double[]> >();
this.Factors = new FactorPotential <double[]> [Outputs];
int[] classOffset = new int[classifier.Classes];
int[] edgeOffset = new int[classifier.Classes];
int[] stateOffset = new int[classifier.Classes];
int[] classCount = new int[classifier.Classes];
int[] edgeCount = new int[classifier.Classes];
int[] stateCount = new int[classifier.Classes];
// Create features for initial class probabilities
for (int c = 0; c < classifier.Classes; c++)
{
var stateParams = new List <double>();
var stateFeatures = new List <IFeature <double[]> >();
var edgeParams = new List <double>();
var edgeFeatures = new List <IFeature <double[]> >();
var classParams = new List <double>();
var classFeatures = new List <IFeature <double[]> >();
var model = classifier[c];
if (includePriors)
{
// Create features for class labels
classParams.Add(Math.Log(classifier.Priors[c]));
classFeatures.Add(new OutputFeature <double[]>(this, c, c));
}
// Create features for initial state probabilities
for (int i = 0; i < model.States; i++)
{
edgeParams.Add(model.Probabilities[i]);
edgeFeatures.Add(new InitialFeature <double[]>(this, c, i));
}
// Create features for state transition probabilities
for (int i = 0; i < model.States; i++)
{
for (int j = 0; j < model.States; j++)
{
edgeParams.Add(model.Transitions[i, j]);
edgeFeatures.Add(new TransitionFeature <double[]>(this, c, i, j));
}
}
// Create features emission probabilities
for (int i = 0; i < model.States; i++)
{
for (int d = 0; d < model.Dimension; d++)
{
double mean = model.Emissions[i].Mean[d];
double var = model.Emissions[i].Variance[d];
double u = -0.5 * (Math.Log(2.0 * Math.PI * var) + (mean * mean) / var);
double m1 = mean / var;
double m2 = -1.0 / (2.0 * var);
// Occupancy
stateParams.Add(u);
stateFeatures.Add(new OccupancyFeature <double[]>(this, c, i));
// 1st Moment (x)
stateParams.Add(m1);
stateFeatures.Add(new MultivariateFirstMomentFeature(this, c, i, d));
// 2nd Moment (x²)
stateParams.Add(m2);
stateFeatures.Add(new MultivariateSecondMomentFeature(this, c, i, d));
}
}
classOffset[c] = factorIndex;
edgeOffset[c] = factorIndex + classParams.Count;
stateOffset[c] = factorIndex + classParams.Count + edgeParams.Count;
classCount[c] = classParams.Count;
edgeCount[c] = edgeParams.Count;
stateCount[c] = stateParams.Count;
// 1. classes
factorFeatures.AddRange(classFeatures);
factorParams.AddRange(classParams);
// 2. edges
factorFeatures.AddRange(edgeFeatures);
factorParams.AddRange(edgeParams);
// 3. states
factorFeatures.AddRange(stateFeatures);
factorParams.AddRange(stateParams);
factorIndex += classParams.Count + stateParams.Count + edgeParams.Count;
}
System.Diagnostics.Debug.Assert(factorIndex == factorParams.Count);
System.Diagnostics.Debug.Assert(factorIndex == factorFeatures.Count);
this.Weights = factorParams.ToArray();
this.Features = factorFeatures.ToArray();
for (int c = 0; c < classifier.Models.Length; c++)
{
Factors[c] = new MarkovMultivariateNormalFactor(this, classifier.Models[c].States, c, Dimensions,
classIndex: classOffset[c], classCount: classCount[c], // 1. classes
edgeIndex: edgeOffset[c], edgeCount: edgeCount[c], // 2. edges
stateIndex: stateOffset[c], stateCount: stateCount[c]); // 3. states
}
}
/// <summary>
/// Creates a new instance of the learning algorithm for a given
/// Markov sequence classifier using the specified configuration
/// function.
/// </summary>
///
public HiddenMarkovClassifierLearning(HiddenMarkovClassifier <TDistribution> classifier,
ClassifierLearningAlgorithmConfiguration algorithm)
: base(classifier, algorithm)
{
}
public void LearnTest2()
{
// Declare some testing data
int[][] inputs = new int[][]
{
new int[] { 0,0,1,2 }, // Class 0
new int[] { 0,1,1,2 }, // Class 0
new int[] { 0,0,0,1,2 }, // Class 0
new int[] { 0,1,2,2,2 }, // Class 0
new int[] { 2,2,1,0 }, // Class 1
new int[] { 2,2,2,1,0 }, // Class 1
new int[] { 2,2,2,1,0 }, // Class 1
new int[] { 2,2,2,2,1 }, // Class 1
};
int[] outputs = new int[]
{
0,0,0,0, // First four sequences are of class 0
1,1,1,1, // Last four sequences are of class 1
};
// We are trying to predict two different classes
int classes = 2;
// Each sequence may have up to 3 symbols (0,1,2)
int symbols = 3;
// Nested models will have 3 states each
int[] states = new int[] { 3, 3 };
// Creates a new Hidden Markov Model Classifier with the given parameters
HiddenMarkovClassifier classifier = new HiddenMarkovClassifier(classes, states, symbols);
// Create a new learning algorithm to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning(classifier.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 0
}
);
// Enable support for sequence rejection
teacher.Rejection = true;
// Train the sequence classifier using the algorithm
double likelihood = teacher.Run(inputs, outputs);
HiddenMarkovModel threshold = classifier.Threshold;
Assert.AreEqual(6, threshold.States);
Assert.AreEqual(classifier.Models[0].Transitions[0, 0], threshold.Transitions[0, 0], 1e-10);
Assert.AreEqual(classifier.Models[0].Transitions[1, 1], threshold.Transitions[1, 1], 1e-10);
Assert.AreEqual(classifier.Models[0].Transitions[2, 2], threshold.Transitions[2, 2], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[0, 0], threshold.Transitions[3, 3], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[1, 1], threshold.Transitions[4, 4], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[2, 2], threshold.Transitions[5, 5], 1e-10);
for (int i = 0; i < 3; i++)
for (int j = 3; j < 6; j++)
Assert.AreEqual(Double.NegativeInfinity, threshold.Transitions[i, j]);
for (int i = 3; i < 6; i++)
for (int j = 0; j < 3; j++)
Assert.AreEqual(Double.NegativeInfinity, threshold.Transitions[i, j]);
Assert.IsFalse(Matrix.HasNaN(threshold.Transitions));
classifier.Sensitivity = 0.5;
// Will assert the models have learned the sequences correctly.
for (int i = 0; i < inputs.Length; i++)
{
int expected = outputs[i];
int actual = classifier.Compute(inputs[i], out likelihood);
Assert.AreEqual(expected, actual);
}
int[] r0 = new int[] { 1, 1, 0, 0, 2 };
double logRejection;
int c = classifier.Compute(r0, out logRejection);
Assert.AreEqual(-1, c);
Assert.AreEqual(0.99906957195279988, logRejection);
Assert.IsFalse(double.IsNaN(logRejection));
logRejection = threshold.Evaluate(r0);
Assert.AreEqual(-4.5653702970734793, logRejection, 1e-10);
Assert.IsFalse(double.IsNaN(logRejection));
threshold.Decode(r0, out logRejection);
Assert.AreEqual(-8.21169955167614, logRejection, 1e-10);
Assert.IsFalse(double.IsNaN(logRejection));
foreach (var model in classifier.Models)
{
double[,] A = model.Transitions;
for (int i = 0; i < A.GetLength(0); i++)
{
double[] row = A.Exp().GetRow(i);
double sum = row.Sum();
Assert.AreEqual(1, sum, 1e-10);
}
}
{
double[,] A = classifier.Threshold.Transitions;
for (int i = 0; i < A.GetLength(0); i++)
{
double[] row = A.GetRow(i);
double sum = row.Exp().Sum();
Assert.AreEqual(1, sum, 1e-6);
}
}
}
public void RecognizeAsync(ISoundSignalReader signal, HiddenMarkovClassifier hmm, Action<string> handleMessage,
SignalVisitor voiceVisitor = null)
{
Action<List<double[]>> action = features =>
{
var observations = _codeBook.Quantize(features.Select(item => new Point(item)).ToArray());
double[] responsabilities;
var ret = hmm.Compute(observations, out responsabilities);
var models = hmm.Models;
var likelyHoodValue = Double.MinValue;
foreach (var model in models)
{
var val = model.Evaluate(observations);
if (val > likelyHoodValue)
{
likelyHoodValue = val;
}
}
handleMessage(hmm[ret].Tag.ToString());
};
var featureUtility = new FeatureUtility(_engineParameters);
featureUtility.ExtractFeaturesAsync(signal, action, voiceVisitor);
}
public TrainResult TrainAll(Dictionary<string, IList<ISoundSignalReader>> signalsDictionary,
SignalVisitor voiceVisitor = null)
{
var numberOfItems = 0;
foreach (var item in signalsDictionary)
{
numberOfItems += item.Value.Count;
}
double[][][][] featuresInput = new Double[signalsDictionary.Count][][][];
int[] models = new int[numberOfItems];
var allSignalIndex = 0;
var modelIndex = 0;
var featureUtility = new FeatureUtility(_engineParameters);
foreach (var item in signalsDictionary)
{
var signals = item.Value; // signals
var signalsCount = signals.Count();
featuresInput[modelIndex] = new double[signalsCount][][];
for (var signalIndex = 0; signalIndex < signalsCount; signalIndex++)
{
var signal = signals[signalIndex];
List<Double[]> features = featureUtility.ExtractFeatures(signal, voiceVisitor).First();
featuresInput[modelIndex][signalIndex] = features.ToArray();
models[allSignalIndex] = modelIndex;
allSignalIndex++;
}
modelIndex++;
}
List<int[]> observables = new List<int[]>();
for (int wordIndex = 0; wordIndex < featuresInput.Length; wordIndex++) // foreach word
{
for (var signalIndex = 0; signalIndex < featuresInput[wordIndex].Length; signalIndex++)
// foreach word signal
{
var points = featuresInput[wordIndex][signalIndex].Select(item => new Point(item));
// convert feature to points
var codeItems = _codeBook.Quantize(points.ToArray());
observables.Add(codeItems);
}
}
//HiddenMarkovModel hmm = new HiddenMarkovModel(5, _codeBook.Size, true);
//var Bauc
var hmm = new HiddenMarkovClassifier(signalsDictionary.Count, new Forward(_numberOfHiddenStates),
_codeBook.Size, signalsDictionary.Keys.ToArray());
const int iterations = 200;
const double tolerance = 0;
var teacher = new HiddenMarkovClassifierLearning(hmm,
i => new ViterbiLearning(hmm.Models[i]) {Iterations = iterations, Tolerance = tolerance}
);
teacher.Run(observables.ToArray(), models);
return new TrainResult {Catalog = _codeBook, Models = hmm.Models.ToArray()};
}
public static HiddenMarkovClassifier <Independent <NormalDistribution> > CreateModel4(out double[][][] words, out int[] labels, bool usePriors)
{
double[][] hello =
{
new double[] { 1.0, 0.1, 0.0, 0.0 }, // let's say the word
new double[] { 0.0, 1.0, 0.1, 0.1 }, // hello took 6 frames
new double[] { 0.0, 1.0, 0.1, 0.1 }, // to be recorded.
new double[] { 0.0, 0.0, 1.0, 0.0 },
new double[] { 0.0, 0.0, 1.0, 0.0 },
new double[] { 0.0, 0.0, 0.1, 1.1 },
};
double[][] car =
{
new double[] { 0.0, 0.0, 0.0, 1.0 }, // the car word
new double[] { 0.1, 0.0, 1.0, 0.1 }, // took only 4.
new double[] { 0.0, 0.0, 0.1, 0.0 },
new double[] { 1.0, 0.0, 0.0, 0.0 },
};
double[][] wardrobe =
{
new double[] { 0.0, 0.0, 1.0, 0.0 }, // same for the
new double[] { 0.1, 0.0, 1.0, 0.1 }, // wardrobe word.
new double[] { 0.0, 0.1, 1.0, 0.0 },
new double[] { 0.1, 0.0, 1.0, 0.1 },
};
double[][] wardrobe2 =
{
new double[] { 0.0, 0.0, 1.0, 0.0 }, // same for the
new double[] { 0.2, 0.0, 1.0, 0.1 }, // wardrobe word.
new double[] { 0.0, 0.1, 1.0, 0.0 },
new double[] { 0.1, 0.0, 1.0, 0.2 },
};
words = new double[][][] { hello, car, wardrobe, wardrobe2 };
labels = new [] { 0, 1, 2, 2 };
var initial = new Independent <NormalDistribution>
(
new NormalDistribution(0, 1),
new NormalDistribution(0, 1),
new NormalDistribution(0, 1),
new NormalDistribution(0, 1)
);
int numberOfWords = 3;
int numberOfStates = 5;
var classifier = new HiddenMarkovClassifier <Independent <NormalDistribution> >
(
classes: numberOfWords,
topology: new Forward(numberOfStates),
initial: initial
);
var teacher = new HiddenMarkovClassifierLearning <Independent <NormalDistribution> >(classifier,
modelIndex => new BaumWelchLearning <Independent <NormalDistribution> >(classifier.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 100,
FittingOptions = new IndependentOptions()
{
InnerOption = new NormalOptions()
{
Regularization = 1e-5
}
}
}
);
if (usePriors)
{
teacher.Empirical = true;
}
double logLikelihood = teacher.Run(words, labels);
Assert.AreEqual(208.38345600145777d, logLikelihood);
return(classifier);
}
public static HiddenMarkovClassifier <Independent> CreateModel3(out double[][][] sequences2, out int[] labels2)
{
sequences2 = new double[][][]
{
new double[][]
{
// This is the first sequence with label = 0
new double[] { 1, 1.12, 2.41, 1.17, 9.3 },
new double[] { 1, 2.54, 1.45, 0.16, 4.5 },
new double[] { 1, 3.46, 2.63, 1.15, 9.2 },
new double[] { 1, 4.73, 0.41, 1.54, 5.5 },
new double[] { 2, 5.81, 2.42, 1.13, 9.1 },
},
new double[][]
{
// This is the first sequence with label = 0
new double[] { 0, 1.49, 2.48, 1.18, 9.37 },
new double[] { 1, 2.18, 1.44, 2.19, 1.56 },
new double[] { 1, 3.77, 2.62, 1.10, 9.25 },
new double[] { 2, 4.76, 5.44, 3.58, 5.54 },
new double[] { 2, 5.85, 2.46, 1.16, 5.13 },
new double[] { 2, 4.84, 5.44, 3.54, 5.52 },
new double[] { 2, 5.83, 3.41, 1.22, 5.11 },
},
new double[][]
{
// This is the first sequence with label = 0
new double[] { 2, 1.11, 2.41, 1.12, 2.31 },
new double[] { 1, 2.52, 3.73, 0.12, 4.50 },
new double[] { 1, 3.43, 2.61, 1.24, 9.29 },
new double[] { 1, 4.74, 2.42, 2.55, 6.57 },
new double[] { 2, 5.85, 2.43, 1.16, 9.16 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 0, 1.26, 5.44, 1.56, 9.55 },
new double[] { 2, 2.67, 5.45, 4.27, 1.54 },
new double[] { 1, 1.28, 3.46, 2.18, 4.13 },
new double[] { 1, 5.89, 2.57, 1.79, 5.02 },
new double[] { 0, 1.40, 2.48, 2.10, 6.41 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 2, 3.21, 2.49, 1.54, 9.17 },
new double[] { 2, 2.62, 5.40, 4.25, 1.54 },
new double[] { 1, 1.53, 6.49, 2.17, 4.52 },
new double[] { 1, 2.84, 2.58, 1.73, 6.04 },
new double[] { 1, 1.45, 2.47, 2.28, 5.42 },
new double[] { 1, 1.46, 2.46, 2.35, 5.41 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 1, 5.27, 5.45, 1.4, 9.5 },
new double[] { 2, 2.68, 2.54, 3.2, 2.2 },
new double[] { 1, 2.89, 3.83, 2.6, 4.1 },
new double[] { 1, 1.80, 1.32, 1.2, 4.2 },
new double[] { 0, 1.41, 2.41, 2.1, 6.4 },
}
};
labels2 = new[] { 0, 0, 0, 1, 1, 1 };
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a multivariate sequence and the same sequence backwards.
var comp1 = new GeneralDiscreteDistribution(3);
var comp2 = new NormalDistribution(1);
var comp3 = new NormalDistribution(2);
var comp4 = new NormalDistribution(3);
var comp5 = new NormalDistribution(4);
var density = new Independent(comp1, comp2, comp3, comp4, comp5);
// Creates a sequence classifier containing 2 hidden Markov Models with 2 states
// and an underlying multivariate mixture of Normal distributions as density.
var classifier = new HiddenMarkovClassifier <Independent>(
2, new Forward(5), density);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning <Independent>(
classifier,
// Train each model until the log-likelihood changes less than 0.0001
modelIndex => new BaumWelchLearning <Independent>(
classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0,
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences2, labels2);
Assert.AreEqual(-3.0493028798326081d, logLikelihood, 1e-10);
return(classifier);
}
public static HiddenMarkovClassifier<Independent> CreateModel3()
{
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a multivariate sequence and the same sequence backwards.
var comp1 = new GeneralDiscreteDistribution(3);
var comp2 = new NormalDistribution(1);
var comp3 = new NormalDistribution(2);
var comp4 = new NormalDistribution(3);
var comp5 = new NormalDistribution(4);
var density = new Independent(comp1, comp2, comp3, comp4, comp5);
// Creates a sequence classifier containing 2 hidden Markov Models with 2 states
// and an underlying multivariate mixture of Normal distributions as density.
var classifier = new HiddenMarkovClassifier<Independent>(
2, new Forward(5), density);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning<Independent>(
classifier,
// Train each model until the log-likelihood changes less than 0.0001
modelIndex => new BaumWelchLearning<Independent>(
classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0,
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences2, labels2);
return classifier;
}
public void SimpleGestureRecognitionTest()
{
// Let's say we would like to do a very simple mechanism for
// gesture recognition. In this example, we will be trying to
// create a classifier that can distinguish between the words
// "hello", "car", and "wardrobe".
// Let's say we decided to acquire some data, and we asked some
// people to perform those words in front of a Kinect camera, and,
// using Microsoft's SDK, we were able to captured the x and y
// coordinates of each hand while the word was being performed.
// Let's say we decided to represent our frames as:
//
// double[] frame = { leftHandX, leftHandY, rightHandX, rightHandY };
//
// Since we captured words, this means we captured sequences of
// frames as we described above. Let's write some of those as
// rough examples to explain how gesture recognition can be done:
double[][] hello =
{
new double[] { 1.0, 0.1, 0.0, 0.0 }, // let's say the word
new double[] { 0.0, 1.0, 0.1, 0.1 }, // hello took 6 frames
new double[] { 0.0, 1.0, 0.1, 0.1 }, // to be recorded.
new double[] { 0.0, 0.0, 1.0, 0.0 },
new double[] { 0.0, 0.0, 1.0, 0.0 },
new double[] { 0.0, 0.0, 0.1, 1.1 },
};
double[][] car =
{
new double[] { 0.0, 0.0, 0.0, 1.0 }, // the car word
new double[] { 0.1, 0.0, 1.0, 0.1 }, // took only 4.
new double[] { 0.0, 0.0, 0.1, 0.0 },
new double[] { 1.0, 0.0, 0.0, 0.0 },
};
double[][] wardrobe =
{
new double[] { 0.0, 0.0, 1.0, 0.0 }, // same for the
new double[] { 0.1, 0.0, 1.0, 0.1 }, // wardrobe word.
new double[] { 0.0, 0.1, 1.0, 0.0 },
new double[] { 0.1, 0.0, 1.0, 0.1 },
};
// Here, please note that a real-world example would involve *lots*
// of samples for each word. Here, we are considering just one from
// each class which is clearly sub-optimal and should _never_ be done
// on practice. For example purposes, however, please disregard this.
// Those are the words we have in our vocabulary:
//
double[][][] words = { hello, car, wardrobe };
// Now, let's associate integer labels with them. This is needed
// for the case where there are multiple samples for each word.
//
int[] labels = { 0, 1, 2 };
// We will create our classifiers assuming an independent
// Gaussian distribution for each component in our feature
// vectors (like assuming a Naive Bayes assumption).
var initial = new Independent <NormalDistribution>
(
new NormalDistribution(0, 1),
new NormalDistribution(0, 1),
new NormalDistribution(0, 1),
new NormalDistribution(0, 1)
);
// Now, we can proceed and create our classifier.
//
int numberOfWords = 3; // we are trying to distinguish between 3 words
int numberOfStates = 5; // this value can be found by trial-and-error
var hmm = new HiddenMarkovClassifier <Independent <NormalDistribution> >
(
classes: numberOfWords,
topology: new Forward(numberOfStates), // word classifiers should use a forward topology
initial: initial
);
// Create a new learning algorithm to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning <Independent <NormalDistribution> >(hmm,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning <Independent <NormalDistribution> >(hmm.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 100,
// This is necessary so the code doesn't blow up when it realize
// there is only one sample per word class. But this could also be
// needed in normal situations as well.
//
FittingOptions = new IndependentOptions()
{
InnerOption = new NormalOptions()
{
Regularization = 1e-5
}
}
}
);
// Finally, we can run the learning algorithm!
double logLikelihood = teacher.Run(words, labels);
// At this point, the classifier should be successfully
// able to distinguish between our three word classes:
//
int tc1 = hmm.Compute(hello);
int tc2 = hmm.Compute(car);
int tc3 = hmm.Compute(wardrobe);
Assert.AreEqual(0, tc1);
Assert.AreEqual(1, tc2);
Assert.AreEqual(2, tc3);
// Now, we can use the Markov classifier to initialize a HCRF
var function = new MarkovMultivariateFunction(hmm);
var hcrf = new HiddenConditionalRandomField <double[]>(function);
// We can check that both are equivalent, although they have
// formulations that can be learned with different methods
//
for (int i = 0; i < words.Length; i++)
{
// Should be the same
int expected = hmm.Compute(words[i]);
int actual = hcrf.Compute(words[i]);
// Should be the same
double h0 = hmm.LogLikelihood(words[i], 0);
double c0 = hcrf.LogLikelihood(words[i], 0);
double h1 = hmm.LogLikelihood(words[i], 1);
double c1 = hcrf.LogLikelihood(words[i], 1);
double h2 = hmm.LogLikelihood(words[i], 2);
double c2 = hcrf.LogLikelihood(words[i], 2);
Assert.AreEqual(expected, actual);
Assert.AreEqual(h0, c0, 1e-10);
Assert.IsTrue(h1.IsRelativelyEqual(c1, 1e-10));
Assert.IsTrue(h2.IsRelativelyEqual(c2, 1e-10));
Assert.IsFalse(double.IsNaN(c0));
Assert.IsFalse(double.IsNaN(c1));
Assert.IsFalse(double.IsNaN(c2));
}
// Now we can learn the HCRF using one of the best learning
// algorithms available, Resilient Backpropagation learning:
// Create a learning algorithm
var rprop = new HiddenResilientGradientLearning <double[]>(hcrf)
{
Iterations = 50,
Tolerance = 1e-5
};
// Run the algorithm and learn the models
double error = rprop.Run(words, labels);
// At this point, the HCRF should be successfully
// able to distinguish between our three word classes:
//
int hc1 = hcrf.Compute(hello);
int hc2 = hcrf.Compute(car);
int hc3 = hcrf.Compute(wardrobe);
Assert.AreEqual(0, hc1);
Assert.AreEqual(1, hc2);
Assert.AreEqual(2, hc3);
}
private static HiddenMarkovClassifier<NormalDistribution> createClassifier(
out double[][] sequences, bool rejection = false)
{
sequences = new double[][]
{
new double[] { 0,1,2,3,4 },
new double[] { 4,3,2,1,0 },
};
int[] labels = { 0, 1 };
NormalDistribution density = new NormalDistribution();
HiddenMarkovClassifier<NormalDistribution> classifier =
new HiddenMarkovClassifier<NormalDistribution>(2, new Ergodic(2), density);
var teacher = new HiddenMarkovClassifierLearning<NormalDistribution>(classifier,
modelIndex => new BaumWelchLearning<NormalDistribution>(classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0
}
);
teacher.Rejection = rejection;
teacher.Run(sequences, labels);
return classifier;
}
public void SaveLoadTest()
{
double[][] hello =
{
new double[] { 1.0, 0.1, 0.0, 0.0 }, // let's say the word
new double[] { 0.0, 1.0, 0.1, 0.1 }, // hello took 6 frames
new double[] { 0.0, 1.0, 0.1, 0.1 }, // to be recorded.
new double[] { 0.0, 0.0, 1.0, 0.0 },
new double[] { 0.0, 0.0, 1.0, 0.0 },
new double[] { 0.0, 0.0, 0.1, 1.1 },
};
double[][] car =
{
new double[] { 0.0, 0.0, 0.0, 1.0 }, // the car word
new double[] { 0.1, 0.0, 1.0, 0.1 }, // took only 4.
new double[] { 0.0, 0.0, 0.1, 0.0 },
new double[] { 1.0, 0.0, 0.0, 0.0 },
};
double[][] wardrobe =
{
new double[] { 0.0, 0.0, 1.0, 0.0 }, // same for the
new double[] { 0.1, 0.0, 1.0, 0.1 }, // wardrobe word.
new double[] { 0.0, 0.1, 1.0, 0.0 },
new double[] { 0.1, 0.0, 1.0, 0.1 },
};
double[][][] words = { hello, car, wardrobe };
int[] labels = { 0, 1, 2 };
var initial = new Independent
(
new NormalDistribution(0, 1),
new NormalDistribution(0, 1),
new NormalDistribution(0, 1),
new NormalDistribution(0, 1)
);
int numberOfWords = 3;
int numberOfStates = 5;
var classifier = new HiddenMarkovClassifier <Independent>
(
classes: numberOfWords,
topology: new Forward(numberOfStates),
initial: initial
);
var teacher = new HiddenMarkovClassifierLearning <Independent>(classifier,
modelIndex => new BaumWelchLearning <Independent>(classifier.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 100,
FittingOptions = new IndependentOptions()
{
InnerOption = new NormalOptions()
{
Regularization = 1e-5
}
}
}
);
double logLikelihood = teacher.Run(words, labels);
var function = new MarkovMultivariateFunction(classifier);
var hcrf = new HiddenConditionalRandomField <double[]>(function);
MemoryStream stream = new MemoryStream();
hcrf.Save(stream);
stream.Seek(0, SeekOrigin.Begin);
var target = HiddenConditionalRandomField <double[]> .Load(stream);
Assert.AreEqual(hcrf.Function.Factors.Length, target.Function.Factors.Length);
for (int i = 0; i < hcrf.Function.Factors.Length; i++)
{
var e = hcrf.Function.Factors[i];
var a = target.Function.Factors[i];
Assert.AreEqual(e.Index, target.Function.Factors[i].Index);
Assert.AreEqual(e.States, target.Function.Factors[i].States);
Assert.AreEqual(e.EdgeParameters.Count, a.EdgeParameters.Count);
Assert.AreEqual(e.EdgeParameters.Offset, a.EdgeParameters.Offset);
Assert.AreEqual(e.FactorParameters.Count, a.FactorParameters.Count);
Assert.AreEqual(e.FactorParameters.Offset, a.FactorParameters.Offset);
Assert.AreEqual(e.OutputParameters.Count, a.OutputParameters.Count);
Assert.AreEqual(e.OutputParameters.Offset, a.OutputParameters.Offset);
Assert.AreEqual(e.StateParameters.Count, a.StateParameters.Count);
Assert.AreEqual(e.StateParameters.Offset, a.StateParameters.Offset);
Assert.AreEqual(target.Function, a.Owner);
Assert.AreEqual(hcrf.Function, e.Owner);
}
Assert.AreEqual(hcrf.Function.Features.Length, target.Function.Features.Length);
for (int i = 0; i < hcrf.Function.Factors.Length; i++)
{
Assert.AreEqual(hcrf.Function.Features[i].GetType(), target.Function.Features[i].GetType());
}
Assert.AreEqual(hcrf.Function.Outputs, target.Function.Outputs);
for (int i = 0; i < hcrf.Function.Weights.Length; i++)
{
Assert.AreEqual(hcrf.Function.Weights[i], target.Function.Weights[i]);
}
}
public static HiddenMarkovClassifier<Independent> CreateModel2(out double[][][] sequences, out int[] labels)
{
sequences = new double[][][]
{
new double[][]
{
// This is the first sequence with label = 0
new double[] { 0, 1.1 },
new double[] { 1, 2.5 },
new double[] { 1, 3.4 },
new double[] { 1, 4.7 },
new double[] { 2, 5.8 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 2, 3.2 },
new double[] { 2, 2.6 },
new double[] { 1, 1.2 },
new double[] { 1, 0.8 },
new double[] { 0, 1.1 },
}
};
labels = new[] { 0, 1 };
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a multivariate sequence and the same sequence backwards.
var comp1 = new GeneralDiscreteDistribution(3);
var comp2 = new NormalDistribution(1);
var density = new Independent(comp1, comp2);
// Creates a sequence classifier containing 2 hidden Markov Models with 2 states
// and an underlying multivariate mixture of Normal distributions as density.
var classifier = new HiddenMarkovClassifier<Independent>(
2, new Ergodic(2), density);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning<Independent>(
classifier,
// Train each model until the log-likelihood changes less than 0.0001
modelIndex => new BaumWelchLearning<Independent>(
classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0,
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences, labels);
return classifier;
}
/// <summary>
/// Constructs a new potential function modeling Hidden Markov Models.
/// </summary>
///
/// <param name="classifier">A hidden Markov sequence classifier.</param>
/// <param name="includePriors">True to include class features (priors), false otherwise.</param>
///
public MarkovMultivariateFunction(HiddenMarkovClassifier <Independent> classifier,
bool includePriors = true)
{
this.Outputs = classifier.Classes;
int factorIndex = 0;
var factorParams = new List <double>();
var factorFeatures = new List <IFeature <double[]> >();
this.Factors = new FactorPotential <double[]> [Outputs];
int[] classOffset = new int[classifier.Classes];
int[] edgeOffset = new int[classifier.Classes];
int[] stateOffset = new int[classifier.Classes];
int[] classCount = new int[classifier.Classes];
int[] edgeCount = new int[classifier.Classes];
int[] stateCount = new int[classifier.Classes];
int[][][] lookupTables = new int[classifier.Classes][][];
// Create features for initial class probabilities
for (int c = 0; c < classifier.Classes; c++)
{
var stateParams = new List <double>();
var stateFeatures = new List <IFeature <double[]> >();
var edgeParams = new List <double>();
var edgeFeatures = new List <IFeature <double[]> >();
var classParams = new List <double>();
var classFeatures = new List <IFeature <double[]> >();
var model = classifier[c];
int[][] lookupTable = new int[model.States][];
for (int i = 0; i < lookupTable.Length; i++)
{
lookupTable[i] = new int[model.Dimension];
}
if (includePriors)
{
// Create features for class labels
classParams.Add(Math.Log(classifier.Priors[c]));
classFeatures.Add(new OutputFeature <double[]>(this, c, c));
}
// Create features for initial state probabilities
for (int i = 0; i < model.States; i++)
{
edgeParams.Add(model.Probabilities[i]);
edgeFeatures.Add(new InitialFeature <double[]>(this, c, i));
}
// Create features for state transition probabilities
for (int i = 0; i < model.States; i++)
{
for (int j = 0; j < model.States; j++)
{
edgeParams.Add(model.Transitions[i, j]);
edgeFeatures.Add(new TransitionFeature <double[]>(this, c, i, j));
}
}
int position = 0;
// Create features emission probabilities
for (int i = 0; i < model.States; i++)
{
for (int d = 0; d < model.Emissions[i].Components.Length; d++)
{
IUnivariateDistribution distribution = model.Emissions[i].Components[d];
NormalDistribution normal = distribution as NormalDistribution;
if (normal != null)
{
double var = normal.Variance;
double mean = normal.Mean;
// Occupancy
stateParams.Add(-0.5 * (Math.Log(2.0 * Math.PI * var) + (mean * mean) / var));
stateFeatures.Add(new OccupancyFeature <double[]>(this, c, i));
lookupTable[i][d] = position;
position++;
// 1st Moment (x)
stateParams.Add(mean / var);
stateFeatures.Add(new MultivariateFirstMomentFeature(this, c, i, d));
position++;
// 2nd Moment (x²)
stateParams.Add(-1.0 / (2.0 * var));
stateFeatures.Add(new MultivariateSecondMomentFeature(this, c, i, d));
position++;
continue;
}
var discrete = distribution as GeneralDiscreteDistribution;
if (discrete != null)
{
lookupTable[i][d] = position;
for (int k = 0; k < discrete.Frequencies.Length; k++)
{
stateParams.Add(Math.Log(discrete.Frequencies[k]));
stateFeatures.Add(new MultivariateEmissionFeature(this, c, i, k, d));
position++;
}
continue;
}
}
}
classOffset[c] = factorIndex;
edgeOffset[c] = factorIndex + classParams.Count;
stateOffset[c] = factorIndex + classParams.Count + edgeParams.Count;
classCount[c] = classParams.Count;
edgeCount[c] = edgeParams.Count;
stateCount[c] = stateParams.Count;
lookupTables[c] = lookupTable;
// 1. classes
factorFeatures.AddRange(classFeatures);
factorParams.AddRange(classParams);
// 2. edges
factorFeatures.AddRange(edgeFeatures);
factorParams.AddRange(edgeParams);
// 3. states
factorFeatures.AddRange(stateFeatures);
factorParams.AddRange(stateParams);
factorIndex += classParams.Count + stateParams.Count + edgeParams.Count;
}
System.Diagnostics.Debug.Assert(factorIndex == factorParams.Count);
System.Diagnostics.Debug.Assert(factorIndex == factorFeatures.Count);
this.Weights = factorParams.ToArray();
this.Features = factorFeatures.ToArray();
for (int c = 0; c < classifier.Models.Length; c++)
{
Factors[c] = new MarkovIndependentFactor(this, classifier.Models[c].States, c, lookupTables[c],
classIndex: classOffset[c], classCount: classCount[c], // 1. classes
edgeIndex: edgeOffset[c], edgeCount: edgeCount[c], // 2. edges
stateIndex: stateOffset[c], stateCount: stateCount[c]); // 3. states
}
}
public void LearnTest7()
{
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a multivariate sequence and the same sequence backwards.
double[][][] sequences = new double[][][]
{
new double[][]
{
// This is the first sequence with label = 0
new double[] { 0, 1 },
new double[] { 1, 2 },
new double[] { 2, 3 },
new double[] { 3, 4 },
new double[] { 4, 5 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 4, 3 },
new double[] { 3, 2 },
new double[] { 2, 1 },
new double[] { 1, 0 },
new double[] { 0, -1 },
}
};
// Labels for the sequences
int[] labels = { 0, 1 };
var initialDensity = new MultivariateNormalDistribution(2);
// Creates a sequence classifier containing 2 hidden Markov Models with 2 states
// and an underlying multivariate mixture of Normal distributions as density.
var classifier = new HiddenMarkovClassifier<MultivariateNormalDistribution>(
classes: 2, topology: new Forward(2), initial: initialDensity);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning<MultivariateNormalDistribution>(
classifier,
// Train each model until the log-likelihood changes less than 0.0001
modelIndex => new BaumWelchLearning<MultivariateNormalDistribution>(
classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0,
FittingOptions = new NormalOptions()
{
Diagonal = true, // only diagonal covariance matrices
Regularization = 1e-5 // avoid non-positive definite errors
}
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences, labels);
// Calculate the probability that the given
// sequences originated from the model
double likelihood, likelihood2;
// Try to classify the 1st sequence (output should be 0)
int c1 = classifier.Compute(sequences[0], out likelihood);
// Try to classify the 2nd sequence (output should be 1)
int c2 = classifier.Compute(sequences[1], out likelihood2);
Assert.AreEqual(0, c1);
Assert.AreEqual(1, c2);
Assert.AreEqual(-24.560663315259973, logLikelihood, 1e-10);
Assert.AreEqual(0.99999999998805045, likelihood, 1e-10);
Assert.AreEqual(0.99999999998805045, likelihood2, 1e-10);
Assert.IsFalse(double.IsNaN(logLikelihood));
Assert.IsFalse(double.IsNaN(likelihood));
Assert.IsFalse(double.IsNaN(likelihood2));
}
public static HiddenMarkovClassifier<MultivariateNormalDistribution> CreateModel3(
int states = 4, bool priors = true)
{
MultivariateNormalDistribution density = new MultivariateNormalDistribution(2);
var classifier = new HiddenMarkovClassifier<MultivariateNormalDistribution>(6,
new Forward(states), density);
string[] labels = { "1", "2", "3", "4", "5", "6" };
for (int i = 0; i < classifier.Models.Length; i++)
classifier.Models[i].Tag = labels[i];
// Create the learning algorithm for the ensemble classifier
var teacher = new HiddenMarkovClassifierLearning<MultivariateNormalDistribution>(classifier,
// Train each model using the selected convergence criteria
i => new BaumWelchLearning<MultivariateNormalDistribution>(classifier.Models[i])
{
Tolerance = 0.1,
Iterations = 0,
FittingOptions = new NormalOptions() { Diagonal = true, Regularization = 1e-10 }
}
);
teacher.Empirical = priors;
// Run the learning algorithm
teacher.Run(inputTest, outputTest);
return classifier;
}
public static HiddenMarkovClassifier<Independent<NormalDistribution>> CreateModel4(out double[][][] words, out int[] labels, bool usePriors)
{
double[][] hello =
{
new double[] { 1.0, 0.1, 0.0, 0.0 }, // let's say the word
new double[] { 0.0, 1.0, 0.1, 0.1 }, // hello took 6 frames
new double[] { 0.0, 1.0, 0.1, 0.1 }, // to be recorded.
new double[] { 0.0, 0.0, 1.0, 0.0 },
new double[] { 0.0, 0.0, 1.0, 0.0 },
new double[] { 0.0, 0.0, 0.1, 1.1 },
};
double[][] car =
{
new double[] { 0.0, 0.0, 0.0, 1.0 }, // the car word
new double[] { 0.1, 0.0, 1.0, 0.1 }, // took only 4.
new double[] { 0.0, 0.0, 0.1, 0.0 },
new double[] { 1.0, 0.0, 0.0, 0.0 },
};
double[][] wardrobe =
{
new double[] { 0.0, 0.0, 1.0, 0.0 }, // same for the
new double[] { 0.1, 0.0, 1.0, 0.1 }, // wardrobe word.
new double[] { 0.0, 0.1, 1.0, 0.0 },
new double[] { 0.1, 0.0, 1.0, 0.1 },
};
double[][] wardrobe2 =
{
new double[] { 0.0, 0.0, 1.0, 0.0 }, // same for the
new double[] { 0.2, 0.0, 1.0, 0.1 }, // wardrobe word.
new double[] { 0.0, 0.1, 1.0, 0.0 },
new double[] { 0.1, 0.0, 1.0, 0.2 },
};
words = new double[][][] { hello, car, wardrobe, wardrobe2 };
labels = new [] { 0, 1, 2, 2 };
var initial = new Independent<NormalDistribution>
(
new NormalDistribution(0, 1),
new NormalDistribution(0, 1),
new NormalDistribution(0, 1),
new NormalDistribution(0, 1)
);
int numberOfWords = 3;
int numberOfStates = 5;
var classifier = new HiddenMarkovClassifier<Independent<NormalDistribution>>
(
classes: numberOfWords,
topology: new Forward(numberOfStates),
initial: initial
);
var teacher = new HiddenMarkovClassifierLearning<Independent<NormalDistribution>>(classifier,
modelIndex => new BaumWelchLearning<Independent<NormalDistribution>>(classifier.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 100,
FittingOptions = new IndependentOptions()
{
InnerOption = new NormalOptions() { Regularization = 1e-5 }
}
}
);
if (usePriors)
teacher.Empirical = true;
double logLikelihood = teacher.Run(words, labels);
return classifier;
}
/// <summary>
/// Creates a new <see cref="HiddenConditionalRandomField{T}"/> from the given <paramref name="classifier"/>.
/// </summary>
///
/// <param name="classifier">The classifier.</param>
///
/// <returns>
/// A <see cref="HiddenConditionalRandomField{T}"/> that implements
/// exactly the same model as the given <paramref name="classifier"/>.
/// </returns>
///
public static HiddenConditionalRandomField <int> FromHiddenMarkov(HiddenMarkovClassifier <GeneralDiscreteDistribution, int> classifier)
{
return(new HiddenConditionalRandomField <int>(new MarkovDiscreteFunction(classifier)));
}
public void StartClassifier()
{
classifer = new HiddenMarkovClassifier<MultivariateNormalDistribution>(models.ToArray());
}
public void LearnTest2()
{
// Declare some testing data
int[][] inputs = new int[][]
{
new int[] { 0,0,1,2 }, // Class 0
new int[] { 0,1,1,2 }, // Class 0
new int[] { 0,0,0,1,2 }, // Class 0
new int[] { 0,1,2,2,2 }, // Class 0
new int[] { 2,2,1,0 }, // Class 1
new int[] { 2,2,2,1,0 }, // Class 1
new int[] { 2,2,2,1,0 }, // Class 1
new int[] { 2,2,2,2,1 }, // Class 1
};
int[] outputs = new int[]
{
0,0,0,0, // First four sequences are of class 0
1,1,1,1, // Last four sequences are of class 1
};
// We are trying to predict two different classes
int classes = 2;
// Each sequence may have up to 3 symbols (0,1,2)
int symbols = 3;
// Nested models will have 3 states each
int[] states = new int[] { 3, 3 };
// Creates a new Hidden Markov Model Classifier with the given parameters
HiddenMarkovClassifier classifier = new HiddenMarkovClassifier(classes, states, symbols);
// Create a new learning algorithm to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning(classifier.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 0
}
);
// Enable support for sequence rejection
teacher.Rejection = true;
// Train the sequence classifier using the algorithm
double likelihood = teacher.Run(inputs, outputs);
HiddenMarkovModel threshold = classifier.Threshold;
Assert.AreEqual(6, threshold.States);
Assert.AreEqual(classifier.Models[0].Transitions[0, 0], threshold.Transitions[0, 0], 1e-10);
Assert.AreEqual(classifier.Models[0].Transitions[1, 1], threshold.Transitions[1, 1], 1e-10);
Assert.AreEqual(classifier.Models[0].Transitions[2, 2], threshold.Transitions[2, 2], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[0, 0], threshold.Transitions[3, 3], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[1, 1], threshold.Transitions[4, 4], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[2, 2], threshold.Transitions[5, 5], 1e-10);
for (int i = 0; i < 3; i++)
for (int j = 3; j < 6; j++)
Assert.AreEqual(Double.NegativeInfinity, threshold.Transitions[i, j]);
for (int i = 3; i < 6; i++)
for (int j = 0; j < 3; j++)
Assert.AreEqual(Double.NegativeInfinity, threshold.Transitions[i, j]);
Assert.IsFalse(Matrix.HasNaN(threshold.Transitions));
classifier.Sensitivity = 0.5;
// Will assert the models have learned the sequences correctly.
for (int i = 0; i < inputs.Length; i++)
{
int expected = outputs[i];
int actual = classifier.Compute(inputs[i], out likelihood);
Assert.AreEqual(expected, actual);
}
int[] r0 = new int[] { 1, 1, 0, 0, 2 };
double logRejection;
int c = classifier.Compute(r0, out logRejection);
Assert.AreEqual(-1, c);
Assert.AreEqual(0.99906957195279988, logRejection);
Assert.IsFalse(double.IsNaN(logRejection));
logRejection = threshold.Evaluate(r0);
Assert.AreEqual(-4.5653702970734793, logRejection, 1e-10);
Assert.IsFalse(double.IsNaN(logRejection));
threshold.Decode(r0, out logRejection);
Assert.AreEqual(-8.21169955167614, logRejection, 1e-10);
Assert.IsFalse(double.IsNaN(logRejection));
foreach (var model in classifier.Models)
{
double[,] A = model.Transitions;
for (int i = 0; i < A.GetLength(0); i++)
{
double[] row = A.Exp().GetRow(i);
double sum = row.Sum();
Assert.AreEqual(1, sum, 1e-10);
}
}
{
double[,] A = classifier.Threshold.Transitions;
for (int i = 0; i < A.GetLength(0); i++)
{
double[] row = A.GetRow(i);
double sum = row.Exp().Sum();
Assert.AreEqual(1, sum, 1e-6);
}
}
}
public void LearnTest9()
{
double[][][] inputs = large_gestures;
int[] outputs = large_outputs;
int states = 5;
int iterations = 100;
double tolerance = 0.01;
bool rejection = true;
double sensitivity = 1E-85;
int dimension = inputs[0][0].Length;
var hmm = new HiddenMarkovClassifier<MultivariateNormalDistribution>(2,
new Forward(states), new MultivariateNormalDistribution(dimension));
// Create the learning algorithm for the ensemble classifier
var teacher = new HiddenMarkovClassifierLearning<MultivariateNormalDistribution>(hmm,
// Train each model using the selected convergence criteria
i => new BaumWelchLearning<MultivariateNormalDistribution>(hmm.Models[i])
{
Tolerance = tolerance,
Iterations = iterations,
FittingOptions = new NormalOptions()
{
Regularization = 1e-5
}
}
);
teacher.Empirical = true;
teacher.Rejection = rejection;
// Run the learning algorithm
double logLikelihood = teacher.Run(inputs, outputs);
hmm.Sensitivity = sensitivity;
for (int i = 0; i < large_gestures.Length; i++)
{
int actual = hmm.Compute(large_gestures[i]);
int expected = large_outputs[i];
Assert.AreEqual(expected,actual);
}
}
/// <summary>
/// Creates a new <see cref="HiddenConditionalRandomField{T}"/> from the given <paramref name="classifier"/>.
/// </summary>
///
/// <param name="classifier">The classifier.</param>
///
/// <returns>
/// A <see cref="HiddenConditionalRandomField{T}"/> that implements
/// exactly the same model as the given <paramref name="classifier"/>.
/// </returns>
///
public static HiddenConditionalRandomField <double[]> FromHiddenMarkov(HiddenMarkovClassifier <MultivariateNormalDistribution, double[]> classifier)
{
return(new HiddenConditionalRandomField <double[]>(new MarkovMultivariateFunction(classifier)));
}
static void runDiscreteDensityHiddenMarkovClassifierLearningExample()
{
// Observation sequences should only contain symbols that are greater than or equal to 0, and lesser than the number of symbols.
int[][] observationSequences =
{
// First class of sequences: starts and ends with zeros, ones in the middle.
new[] { 0, 1, 1, 1, 0 },
new[] { 0, 0, 1, 1, 0, 0 },
new[] { 0, 1, 1, 1, 1, 0 },
// Second class of sequences: starts with twos and switches to ones until the end.
new[] { 2, 2, 2, 2, 1, 1, 1, 1, 1 },
new[] { 2, 2, 1, 2, 1, 1, 1, 1, 1 },
new[] { 2, 2, 2, 2, 2, 1, 1, 1, 1 },
// Third class of sequences: can start with any symbols, but ends with three.
new[] { 0, 0, 1, 1, 3, 3, 3, 3 },
new[] { 0, 0, 0, 3, 3, 3, 3 },
new[] { 1, 0, 1, 2, 2, 2, 3, 3 },
new[] { 1, 1, 2, 3, 3, 3, 3 },
new[] { 0, 0, 1, 1, 3, 3, 3, 3 },
new[] { 2, 2, 0, 3, 3, 3, 3 },
new[] { 1, 0, 1, 2, 3, 3, 3, 3 },
new[] { 1, 1, 2, 3, 3, 3, 3 },
};
// Consider their respective class labels.
// Class labels have to be zero-based and successive integers.
int[] classLabels =
{
0, 0, 0, // Sequences 1-3 are from class 0.
1, 1, 1, // Sequences 4-6 are from class 1.
2, 2, 2, 2, 2, 2, 2, 2 // Sequences 7-14 are from class 2.
};
// Use a single topology for all inner models.
ITopology forward = new Forward(states: 3);
// Create a hidden Markov classifier with the given topology.
HiddenMarkovClassifier hmc = new HiddenMarkovClassifier(classes: 3, topology: forward, symbols: 4);
// Create a algorithms to teach each of the inner models.
var trainer = new HiddenMarkovClassifierLearning(
hmc,
// Specify individual training options for each inner model.
modelIndex => new BaumWelchLearning(hmc.Models[modelIndex])
{
Tolerance = 0.001, // iterate until log-likelihood changes less than 0.001.
Iterations = 0 // don't place an upper limit on the number of iterations.
}
);
// Call its Run method to start learning.
double averageLogLikelihood = trainer.Run(observationSequences, classLabels);
Console.WriteLine("average log-likelihood for the observations = {0}", averageLogLikelihood);
// Check the output classificaton label for some sequences.
int y1 = hmc.Compute(new[] { 0, 1, 1, 1, 0 }); // output is y1 = 0.
Console.WriteLine("output class = {0}", y1);
int y2 = hmc.Compute(new[] { 0, 0, 1, 1, 0, 0 }); // output is y2 = 0.
Console.WriteLine("output class = {0}", y2);
int y3 = hmc.Compute(new[] { 2, 2, 2, 2, 1, 1 }); // output is y3 = 1.
Console.WriteLine("output class = {0}", y3);
int y4 = hmc.Compute(new[] { 2, 2, 1, 1 }); // output is y4 = 1.
Console.WriteLine("output class = {0}", y4);
int y5 = hmc.Compute(new[] { 0, 0, 1, 3, 3, 3 }); // output is y5 = 2.
Console.WriteLine("output class = {0}", y4);
int y6 = hmc.Compute(new[] { 2, 0, 2, 2, 3, 3 }); // output is y6 = 2.
Console.WriteLine("output class = {0}", y6);
}
/// <summary>
/// Creates a new <see cref="HiddenConditionalRandomField{T}"/> from the given <paramref name="classifier"/>.
/// </summary>
///
/// <param name="classifier">The classifier.</param>
///
/// <returns>
/// A <see cref="HiddenConditionalRandomField{T}"/> that implements
/// exactly the same model as the given <paramref name="classifier"/>.
/// </returns>
///
public static HiddenConditionalRandomField <double> FromHiddenMarkov(HiddenMarkovClassifier <NormalDistribution, double> classifier)
{
return(new HiddenConditionalRandomField <double>(new MarkovContinuousFunction(classifier)));
}
public void LogForwardTest3()
{
MultivariateNormalDistribution density = new MultivariateNormalDistribution(3);
var hmm = new HiddenMarkovClassifier<MultivariateNormalDistribution>(2, new Ergodic(2), density);
double[][][] inputs =
{
new [] { new double[] { 0, 1, 0 }, new double[] { 0, 1, 0 }, new double[] { 0, 1, 0 } },
new [] { new double[] { 1, 6, 2 }, new double[] { 2, 1, 6 }, new double[] { 1, 1, 0 } },
new [] { new double[] { 9, 1, 0 }, new double[] { 0, 1, 5 }, new double[] { 0, 0, 0 } },
};
int[] outputs =
{
0, 0, 1
};
var function = new MarkovMultivariateFunction(hmm);
var observations = inputs[0];
double[,] expected = Matrix.Log(Accord.Statistics.Models.Fields.
ForwardBackwardAlgorithm.Forward(function.Factors[0], observations, 0));
double logLikelihood;
double[,] actual = Accord.Statistics.Models.Fields.
ForwardBackwardAlgorithm.LogForward(function.Factors[0], observations, 0, out logLikelihood);
Assert.IsTrue(expected.IsEqual(actual, 1e-10));
double p = 0;
for (int i = 0; i < hmm[0].States; i++)
p += Math.Exp(actual[observations.Length - 1, i]);
Assert.AreEqual(Math.Exp(logLikelihood), p, 1e-8);
Assert.IsFalse(double.IsNaN(p));
}
public static HiddenMarkovClassifier<MultivariateNormalDistribution> CreateModel2()
{
// Create a Continuous density Hidden Markov Model Sequence Classifier
// to detect a multivariate sequence and the same sequence backwards.
double[][][] sequences = new double[][][]
{
new double[][]
{
// This is the first sequence with label = 0
new double[] { 0, 1 },
new double[] { 1, 2 },
new double[] { 2, 3 },
new double[] { 3, 4 },
new double[] { 4, 5 },
},
new double[][]
{
// This is the second sequence with label = 1
new double[] { 4, 3 },
new double[] { 3, 2 },
new double[] { 2, 1 },
new double[] { 1, 0 },
new double[] { 0, -1 },
}
};
// Labels for the sequences
int[] labels = { 0, 1 };
var density = new MultivariateNormalDistribution(2);
// Creates a sequence classifier containing 2 hidden Markov Models with 2 states
// and an underlying multivariate mixture of Normal distributions as density.
var classifier = new HiddenMarkovClassifier<MultivariateNormalDistribution>(
2, new Ergodic(2), density);
// Configure the learning algorithms to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning<MultivariateNormalDistribution>(
classifier,
// Train each model until the log-likelihood changes less than 0.0001
modelIndex => new BaumWelchLearning<MultivariateNormalDistribution>(
classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0,
FittingOptions = new NormalOptions() { Diagonal = true }
}
);
// Train the sequence classifier using the algorithm
double logLikelihood = teacher.Run(sequences, labels);
return classifier;
}
static void runDiscreteDensityHiddenMarkovClassifierLearningExample()
{
// Observation sequences should only contain symbols that are greater than or equal to 0, and lesser than the number of symbols.
int[][] observationSequences =
{
// First class of sequences: starts and ends with zeros, ones in the middle.
new[] { 0, 1, 1, 1, 0 },
new[] { 0, 0, 1, 1,0, 0 },
new[] { 0, 1, 1, 1,1, 0 },
// Second class of sequences: starts with twos and switches to ones until the end.
new[] { 2, 2, 2, 2,1, 1, 1, 1, 1 },
new[] { 2, 2, 1, 2,1, 1, 1, 1, 1 },
new[] { 2, 2, 2, 2,2, 1, 1, 1, 1 },
// Third class of sequences: can start with any symbols, but ends with three.
new[] { 0, 0, 1, 1,3, 3, 3, 3 },
new[] { 0, 0, 0, 3,3, 3, 3 },
new[] { 1, 0, 1, 2,2, 2, 3, 3 },
new[] { 1, 1, 2, 3,3, 3, 3 },
new[] { 0, 0, 1, 1,3, 3, 3, 3 },
new[] { 2, 2, 0, 3,3, 3, 3 },
new[] { 1, 0, 1, 2,3, 3, 3, 3 },
new[] { 1, 1, 2, 3,3, 3, 3 },
};
// Consider their respective class labels.
// Class labels have to be zero-based and successive integers.
int[] classLabels =
{
0, 0, 0, // Sequences 1-3 are from class 0.
1, 1, 1, // Sequences 4-6 are from class 1.
2, 2, 2, 2, 2, 2, 2, 2 // Sequences 7-14 are from class 2.
};
// Use a single topology for all inner models.
ITopology forward = new Forward(states: 3);
// Create a hidden Markov classifier with the given topology.
HiddenMarkovClassifier hmc = new HiddenMarkovClassifier(classes: 3, topology: forward, symbols: 4);
// Create a algorithms to teach each of the inner models.
var trainer = new HiddenMarkovClassifierLearning(
hmc,
// Specify individual training options for each inner model.
modelIndex => new BaumWelchLearning(hmc.Models[modelIndex])
{
Tolerance = 0.001, // iterate until log-likelihood changes less than 0.001.
Iterations = 0 // don't place an upper limit on the number of iterations.
}
);
// Call its Run method to start learning.
double averageLogLikelihood = trainer.Run(observationSequences, classLabels);
Console.WriteLine("average log-likelihood for the observations = {0}", averageLogLikelihood);
// Check the output classificaton label for some sequences.
int y1 = hmc.Compute(new[] { 0, 1, 1, 1, 0 }); // output is y1 = 0.
Console.WriteLine("output class = {0}", y1);
int y2 = hmc.Compute(new[] { 0, 0, 1, 1, 0, 0 }); // output is y2 = 0.
Console.WriteLine("output class = {0}", y2);
int y3 = hmc.Compute(new[] { 2, 2, 2, 2, 1, 1 }); // output is y3 = 1.
Console.WriteLine("output class = {0}", y3);
int y4 = hmc.Compute(new[] { 2, 2, 1, 1 }); // output is y4 = 1.
Console.WriteLine("output class = {0}", y4);
int y5 = hmc.Compute(new[] { 0, 0, 1, 3, 3, 3 }); // output is y5 = 2.
Console.WriteLine("output class = {0}", y4);
int y6 = hmc.Compute(new[] { 2, 0, 2, 2, 3, 3 }); // output is y6 = 2.
Console.WriteLine("output class = {0}", y6);
}
private static HiddenMarkovClassifier createClassifier(
out int[][] sequences, bool rejection = false)
{
sequences = new int[][]
{
new int[] { 0,1,2,3,4 },
new int[] { 4,3,2,1,0 },
};
int[] labels = { 0, 1 };
HiddenMarkovClassifier classifier =
new HiddenMarkovClassifier(2, new Ergodic(2), symbols: 5);
var teacher = new HiddenMarkovClassifierLearning(classifier,
modelIndex => new BaumWelchLearning(classifier.Models[modelIndex])
{
Tolerance = 0.0001,
Iterations = 0
}
);
teacher.Rejection = rejection;
teacher.Run(sequences, labels);
return classifier;
}
public void LearnTest2()
{
// Declare some testing data
int[][] inputs = new int[][]
{
new int[] { 0,0,1,2 }, // Class 0
new int[] { 0,1,1,2 }, // Class 0
new int[] { 0,0,0,1,2 }, // Class 0
new int[] { 0,1,2,2,2 }, // Class 0
new int[] { 2,2,1,0 }, // Class 1
new int[] { 2,2,2,1,0 }, // Class 1
new int[] { 2,2,2,1,0 }, // Class 1
new int[] { 2,2,2,2,1 }, // Class 1
};
int[] outputs = new int[]
{
0,0,0,0, // First four sequences are of class 0
1,1,1,1, // Last four sequences are of class 1
};
// We are trying to predict two different classes
int classes = 2;
// Each sequence may have up to 3 symbols (0,1,2)
int symbols = 3;
// Nested models will have 3 states each
int[] states = new int[] { 3, 3 };
// Creates a new Hidden Markov Model Classifier with the given parameters
HiddenMarkovClassifier classifier = new HiddenMarkovClassifier(classes, states, symbols);
// Create a new learning algorithm to train the sequence classifier
var teacher = new HiddenMarkovClassifierLearning(classifier,
// Train each model until the log-likelihood changes less than 0.001
modelIndex => new BaumWelchLearning(classifier.Models[modelIndex])
{
Tolerance = 0.001,
Iterations = 0
}
);
// Enable support for sequence rejection
teacher.Rejection = true;
// Train the sequence classifier using the algorithm
double likelihood = teacher.Run(inputs, outputs);
// Will assert the models have learned the sequences correctly.
for (int i = 0; i < inputs.Length; i++)
{
int expected = outputs[i];
int actual = classifier.Compute(inputs[i], out likelihood);
Assert.AreEqual(expected, actual);
}
HiddenMarkovModel threshold = classifier.Threshold;
Assert.AreEqual(6, threshold.States);
Assert.AreEqual(classifier.Models[0].Transitions[0, 0], threshold.Transitions[0, 0], 1e-10);
Assert.AreEqual(classifier.Models[0].Transitions[1, 1], threshold.Transitions[1, 1], 1e-10);
Assert.AreEqual(classifier.Models[0].Transitions[2, 2], threshold.Transitions[2, 2], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[0, 0], threshold.Transitions[3, 3], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[1, 1], threshold.Transitions[4, 4], 1e-10);
Assert.AreEqual(classifier.Models[1].Transitions[2, 2], threshold.Transitions[5, 5], 1e-10);
Assert.IsFalse(Matrix.HasNaN(threshold.Transitions));
int[] r0 = new int[] { 1, 1, 0, 0, 2 };
double logRejection;
int c = classifier.Compute(r0, out logRejection);
Assert.AreEqual(-1, c);
Assert.AreEqual(0.99569011079012049, logRejection);
Assert.IsFalse(double.IsNaN(logRejection));
logRejection = threshold.Evaluate(r0);
Assert.AreEqual(-6.7949285513628528, logRejection, 1e-10);
Assert.IsFalse(double.IsNaN(logRejection));
threshold.Decode(r0, out logRejection);
Assert.AreEqual(-8.902077561009957, logRejection, 1e-10);
Assert.IsFalse(double.IsNaN(logRejection));
}
private void btnLearnHMM_Click(object sender, EventArgs e)
{
if (gridSamples.Rows.Count == 0)
{
MessageBox.Show("Please load or insert some data first.");
return;
}
BindingList <Sequence> samples = database.Samples;
BindingList <String> classes = database.Classes;
double[][][] inputs = new double[samples.Count][][];
int[] outputs = new int[samples.Count];
for (int i = 0; i < inputs.Length; i++)
{
inputs[i] = samples[i].Input;
outputs[i] = samples[i].Output;
}
int states = 5;
int iterations = 0;
double tolerance = 0.01;
bool rejection = false;
hmm = new HiddenMarkovClassifier <MultivariateNormalDistribution, double[]>(classes.Count,
new Forward(states), new MultivariateNormalDistribution(2), classes.ToArray());
// Create the learning algorithm for the ensemble classifier
var teacher = new HiddenMarkovClassifierLearning <MultivariateNormalDistribution, double[]>(hmm)
{
// Train each model using the selected convergence criteria
Learner = i => new BaumWelchLearning <MultivariateNormalDistribution, double[]>(hmm.Models[i])
{
Tolerance = tolerance,
Iterations = iterations,
FittingOptions = new NormalOptions()
{
Regularization = 1e-5
}
}
};
teacher.Empirical = true;
teacher.Rejection = rejection;
// Run the learning algorithm
teacher.Learn(inputs, outputs);
// Classify all training instances
foreach (var sample in database.Samples)
{
sample.RecognizedAs = hmm.Decide(sample.Input);
}
foreach (DataGridViewRow row in gridSamples.Rows)
{
var sample = row.DataBoundItem as Sequence;
row.DefaultCellStyle.BackColor = (sample.RecognizedAs == sample.Output) ?
Color.LightGreen : Color.White;
}
btnLearnHCRF.Enabled = true;
hcrf = null;
}
public void GradientTest()
{
// Creates a sequence classifier containing 2 hidden Markov Models
// with 2 states and an underlying Normal distribution as density.
MultivariateNormalDistribution density = new MultivariateNormalDistribution(3);
var hmm = new HiddenMarkovClassifier<MultivariateNormalDistribution>(2, new Ergodic(2), density);
double[][][] inputs =
{
new [] { new double[] { 0, 1, 0 }, new double[] { 0, 1, 0 }, new double[] { 0, 1, 0 } },
new [] { new double[] { 1, 6, 2 }, new double[] { 2, 1, 6 }, new double[] { 1, 1, 0 } },
new [] { new double[] { 9, 1, 0 }, new double[] { 0, 1, 5 }, new double[] { 0, 0, 0 } },
};
int[] outputs =
{
0, 0, 1
};
var function = new MarkovMultivariateFunction(hmm);
var model = new HiddenConditionalRandomField<double[]>(function);
var target = new ForwardBackwardGradient<double[]>(model);
FiniteDifferences diff = new FiniteDifferences(function.Weights.Length);
diff.Function = parameters => func(model, parameters, inputs, outputs);
double[] expected = diff.Compute(function.Weights);
double[] actual = target.Gradient(function.Weights, inputs, outputs);
for (int i = 0; i < actual.Length; i++)
{
Assert.AreEqual(expected[i], actual[i], 0.05);
Assert.IsFalse(double.IsNaN(actual[i]));
Assert.IsFalse(double.IsNaN(expected[i]));
}
}
