/// <summary>
/// Creates a deep copy
/// </summary>
public INonRecurrentNetwork DeepClone()
{
ParallelPerceptron clone = new ParallelPerceptron(NumOfInputValues, NumOfGates, Resolution);
clone.SetWeights(_flatWeights);
return(clone);
}
//Constructor
/// <summary>
/// Constructs a parallel perceptron P-Delta rule trainer
/// </summary>
/// <param name="net">PP to be trained</param>
/// <param name="inputVectorCollection">Predictors (input)</param>
/// <param name="outputVectorCollection">Ideal outputs (the same number of rows as predictors rows)</param>
/// <param name="settings">Optional startup parameters of the trainer</param>
public PDeltaRuleTrainer(ParallelPerceptron net,
List <double[]> inputVectorCollection,
List <double[]> outputVectorCollection,
PDeltaRuleTrainerSettings settings = null
)
{
//Parameters
_settings = settings;
if (_settings == null)
{
//Default parameters
_settings = new PDeltaRuleTrainerSettings();
}
_net = net;
_inputVectorCollection = inputVectorCollection;
_outputVectorCollection = outputVectorCollection;
_resSquashCoeff = _net.ResSquashCoeff;
_acceptableError = 1d / (2d * _resSquashCoeff);
_marginSignificance = 1;
_clearMargin = 0.05;
_minM = _acceptableError * _resSquashCoeff;
_maxM = 4d * _minM;
_learningRate = _settings.IniLR;
_prevWeights = _net.GetWeights();
_prevMSE = 0;
_currMSE = 0;
_epoch = 0;
//Parallel workers / batch ranges preparation
_workerRangeCollection = new List <WorkerRange>();
int numOfWorkers = Math.Min(Environment.ProcessorCount, _inputVectorCollection.Count);
numOfWorkers = Math.Max(1, numOfWorkers);
int workerBatchSize = _inputVectorCollection.Count / numOfWorkers;
for (int workerIdx = 0, fromRow = 0; workerIdx < numOfWorkers; workerIdx++, fromRow += workerBatchSize)
{
int toRow = 0;
if (workerIdx == numOfWorkers - 1)
{
toRow = _inputVectorCollection.Count - 1;
}
else
{
toRow = (fromRow + workerBatchSize) - 1;
}
WorkerRange workerRange = new WorkerRange(fromRow, toRow, _net.NumOfWeights);
_workerRangeCollection.Add(workerRange);
}
return;
}
//Constructor
/// <summary>
/// Constructs a parallel perceptron P-Delta rule trainer
/// </summary>
/// <param name="net">PP to be trained</param>
/// <param name="inputVectorCollection">Predictors (input)</param>
/// <param name="outputVectorCollection">Ideal outputs (the same number of rows as predictors rows)</param>
/// <param name="settings">Configuration of the trainer</param>
/// <param name="rand">Random object to be used</param>
public PDeltaRuleTrainer(ParallelPerceptron net,
List <double[]> inputVectorCollection,
List <double[]> outputVectorCollection,
PDeltaRuleTrainerSettings settings,
Random rand
)
{
//Parameters
_settings = (PDeltaRuleTrainerSettings)settings.DeepClone();
MaxAttempt = _settings.NumOfAttempts;
MaxAttemptEpoch = _settings.NumOfAttemptEpochs;
_net = net;
_rand = rand;
_inputVectorCollection = inputVectorCollection;
_outputVectorCollection = outputVectorCollection;
_resSquashCoeff = _net.ResSquashCoeff;
_acceptableError = 1d / (2d * _resSquashCoeff);
_marginSignificance = 1;
_clearMargin = 0.05;
_minM = _acceptableError * _resSquashCoeff;
_maxM = 4d * _minM;
//Parallel workers / batch ranges preparation
_workerRangeCollection = new List <WorkerRange>();
int numOfWorkers = Math.Min(Environment.ProcessorCount, _inputVectorCollection.Count);
numOfWorkers = Math.Max(1, numOfWorkers);
int workerBatchSize = _inputVectorCollection.Count / numOfWorkers;
for (int workerIdx = 0, fromRow = 0; workerIdx < numOfWorkers; workerIdx++, fromRow += workerBatchSize)
{
int toRow = 0;
if (workerIdx == numOfWorkers - 1)
{
toRow = _inputVectorCollection.Count - 1;
}
else
{
toRow = (fromRow + workerBatchSize) - 1;
}
WorkerRange workerRange = new WorkerRange(fromRow, toRow, _net.NumOfWeights);
_workerRangeCollection.Add(workerRange);
}
InfoMessage = string.Empty;
//Start training attempt
Attempt = 0;
NextAttempt();
return;
}
