public void GetErrorTest()
{
IBackPropagation target = CreateIBackPropagation(); // TODO: Initialize to an appropriate value
double expected = 0F; // TODO: Initialize to an appropriate value
double actual;
actual = target.GetError();
Assert.AreEqual(expected, actual);
Assert.Inconclusive("Verify the correctness of this test method.");
}
public bool Train()
{
double currentError = 0;
int currentIteration = 0;
NeuralEventArgs Args = new NeuralEventArgs();
do
{
currentError = 0;
foreach (KeyValuePair <T, double[]> p in TrainingSet)
{
NeuralNet.ForwardPropagate(p.Value, p.Key);
NeuralNet.BackPropagate();
currentError += NeuralNet.GetError();
}
currentIteration++;
if (IterationChanged != null && currentIteration % 5 == 0)
{
Args.CurrentError = currentError;
Args.CurrentIteration = currentIteration;
IterationChanged(this, Args);
}
} while (currentError > maximumError && currentIteration < maximumIteration && !Args.Stop);
if (IterationChanged != null)
{
Args.CurrentError = currentError;
Args.CurrentIteration = currentIteration;
IterationChanged(this, Args);
}
if (currentIteration >= maximumIteration || Args.Stop)
{
return(false);
}
return(true);
}
public bool Train()
{
double currentError = 0;
int currentIteration = 0;
NeuralEventArgs Args = new NeuralEventArgs();
do
{
currentError = 0;
foreach (FaceImage face in _trainingSet)
{
_neuralNet.ForwardPropagate(face.VectorInNet, face.PersonId);
_neuralNet.BackPropagate();
currentError += _neuralNet.GetError();
}
currentIteration++;
if (IterationChanged != null && currentIteration % 5 == 0)
{
Args.CurrentError = currentError;
Args.CurrentIteration = currentIteration;
IterationChanged(this, Args);
}
} while (currentError > _maxError && currentIteration < _maxIter && !Args.Stop);
if (IterationChanged != null)
{
Args.CurrentError = currentError;
Args.CurrentIteration = currentIteration;
IterationChanged(this, Args);
}
if (currentIteration >= _maxIter || Args.Stop)
{
return(false);//Training Not Successful
}
return(true);
}
public bool Train()
{
double currentError = 0;
int currentIteration = 0;
NeuralEventArgs Args = new NeuralEventArgs();
do
{
currentError = 0;
Random r = new Random();
foreach (KeyValuePair <string, double[]> pattern in _distractionTrainingSet.OrderBy(x => r.Next()))
{
_neuralNet.ForwardPropagate(pattern.Value, pattern.Key[0].ToString());
_neuralNet.BackPropagate();
currentError += _neuralNet.GetError();
}
currentIteration++;
if (currentIteration % 5 == 0)
{
ViewModel.CurrentError = currentError;
ViewModel.CurrentIteration = currentIteration;
}
if (currentIteration % 10 == 0)
{
List <string> toRemoved = new List <string>();
bool isOver = true;
foreach (var samplePattern in _settingsModel.SampleTrainingSet)
{
Recognize(samplePattern.Value, _recognizeModel);
if (samplePattern.Key[0].Equals(_recognizeModel.MatchedHigh[0]) && _recognizeModel.OutputHightValue >= 0.1)
{
toRemoved.Add(samplePattern.Key);
// _trainingSet.Remove(samplePattern.Key);
}
else
{
// currentError = 0.1;
isOver = false;
//isOver = true;
}
}
if (isOver)
{
foreach (var patternToremove in toRemoved)
{
_settingsModel.SampleTrainingSet.Remove(patternToremove);
}
}
}
} while (currentError > ViewModel.MaximumError && currentIteration < MaximumIteration);
if (Math.Abs(currentError) < 0.001 && currentIteration != 0)
{
ViewModel.CurrentError = currentError;
ViewModel.CurrentIteration = currentIteration;
}
if (currentIteration >= MaximumIteration)
{
return(false);//Training Not Successful
}
return(true);
}
