public void ExecutePlan(IPlan plan, MorphoSyntacticContext initialContext)
{
var baseAction = TrainingAction.ImplementPlan(plan, _vectors, _contextMaps);
//todo - could loop to reduce error
var error = baseAction.Train(_network,initialContext);
baseAction.SaveContexts(_contextMaps);
}
public static MorphoSyntacticContext InitialState()
{
var result = new MorphoSyntacticContext {Elements = new double[VectorLength]};
var r = new Random();
for (var i = 0; i < result.Elements.Length; i++)
{
result.Elements[i] = r.NextDouble()*Epsilon;
}
return result;
}
public virtual double Train(INeuralNetwork network, MorphoSyntacticContext context)
{
var error = 0.0;
var denominator = 0.0;
foreach (var contained in ChildActions)
{
denominator += 1.0;
error += contained.Train(network, context);
}
return (denominator > 0.0 ? error/denominator : 0.0);
}
public override double Train(INeuralNetwork network, MorphoSyntacticContext context)
{
if (_inputArray == null && _wordVector != null)
{
_inputArray = new double[_wordVector.Elements.Length + context.Elements.Length];
_wordVector.Elements.CopyTo(_inputArray, 0);
}
if (_inputArray == null) return base.Train(network, context);
context.Elements.CopyTo(_inputArray, WordVector.VectorLength);
var example = new Example {Input = _inputArray, ExpectedResult = _outputArray};
network.Theta.LoadFrom(_weights);
var error = network.Train(example, 0.01);
network.Theta.SaveTo(ref _weights);
var childContext = new MorphoSyntacticContext(network.HiddenLayer);
error = (error + base.Train(network, childContext)/2.0);
return error;
}
public Example(WordVector word, MorphoSyntacticContext context, double[] target )
{
Input = new double[WordVector.VectorLength + MorphoSyntacticContext.VectorLength];
word.Elements.CopyTo(Input,0);
context.Elements.CopyTo(Input, WordVector.VectorLength);
ExpectedResult = target;
}