public NeuralTyresEntry Conjure(params double[] input)
{
var name = Sources.Select(x => x.Name).GroupBy(x => x).MaxEntry(x => x.Count()).Key;
var shortName = Sources.Select(x => x.ShortName).GroupBy(x => x).MaxEntry(x => x.Count()).Key;
var result = new NeuralTyresEntry(name, shortName, TyresVersion);
SetInputs(input, result);
if (_singleNetwork != null)
{
var data = _singleNetwork.Compute(input);
if (data.Length != _outputKeys.Length)
{
throw new Exception($"Amount of computed data doesn’t match output keys: {data.Length}≠{_outputKeys.Length}");
}
for (var i = 0; i < _outputKeys.Length; i++)
{
SetValue(result, _outputKeys[i], _outputNormalizations[i].Denormalize(data[i]));
}
}
else if (_networks != null)
{
for (var i = 0; i < _networks.Length; i++)
{
SetValue(result, _outputKeys[i], _outputNormalizations[i].Denormalize(_networks[i].Compute(input)[0]));
}
}
else
{
throw new Exception("Invalid state");
}
return(result);
}
public void Learn(INeuralNetwork net, ILearningSequence<ISupervisedLearningVector> seq)
{
LearningStory = new List<NeuronState>();
bool isLearned = true;
do
{
StoreState(net);
isLearned = true;
IEnumerator<ISupervisedLearningVector> en = seq.Vectors.GetEnumerator();
while (en.MoveNext())
{
net.SetInput(en.Current.Data);
net.Compute();
double delta = en.Current.CorrectOutput - net[0];
if (delta != 0.0)
{
isLearned = false;
CorrectWeights(net, delta > 0 ? 1.0 : -1.0);
}
}
seq.Shuffle();
} while (!isLearned);
StoreState(net);
}
public void Learn(INeuralNetwork net, ILearningSequence<ISupervisedLearningVector> seq)
{
LearningStory = new List<NeuronState>();
bool isLearned = true;
int counter = 0;
do
{
StoreState(net);
isLearned = true;
IEnumerator<ISupervisedLearningVector> en = seq.Vectors.GetEnumerator();
while (en.MoveNext())
{
net.SetInput(en.Current.Data);
net.Compute();
CorrectWeights(net, en.Current.CorrectOutput - net.Layers[1][0].Potential);
}
en.Reset();
while (en.MoveNext())
{
net.SetInput(en.Current.Data);
net.Compute();
if (Math.Abs(en.Current.CorrectOutput - net[0]) > Epsilon)
{
isLearned = false;
break;
}
}
seq.Shuffle();
counter++;
} while (!isLearned && counter < EpochLimit);
StoreState(net);
Failed = !isLearned;
}
public List <float> Compute(List <float> inputs)
{
return(neuralNetwork.Compute(inputs));
}