private void EmpiricalCounts(int[][][][] data, int[][] labels)
{
Ehat = Empty2D();
for (int m = 0; m < data.Length; m++)
{
int[][][] dataDoc = data[m];
int[] labelsDoc = labels[m];
int[] label = new int[window];
//Arrays.fill(label, classIndex.indexOf("O"));
Arrays.Fill(label, classIndex.IndexOf(backgroundSymbol));
for (int i = 0; i < dataDoc.Length; i++)
{
System.Array.Copy(label, 1, label, 0, window - 1);
label[window - 1] = labelsDoc[i];
for (int j = 0; j < dataDoc[i].Length; j++)
{
int[] cliqueLabel = new int[j + 1];
System.Array.Copy(label, window - 1 - j, cliqueLabel, 0, j + 1);
CRFLabel crfLabel = new CRFLabel(cliqueLabel);
int labelIndex = labelIndices[j].IndexOf(crfLabel);
//log.info(crfLabel + " " + labelIndex);
for (int k = 0; k < dataDoc[i][j].Length; k++)
{
Ehat[dataDoc[i][j][k]][labelIndex]++;
}
}
}
}
}
private void ComputeEHat()
{
Ehat = Empty2D();
for (int m = 0; m < data.Length; m++)
{
int[][][] docData = data[m];
int[] docLabels = labels[m];
int[] windowLabels = new int[window];
Arrays.Fill(windowLabels, classIndex.IndexOf(backgroundSymbol));
if (docLabels.Length > docData.Length)
{
// only true for self-training
// fill the windowLabel array with the extra docLabels
System.Array.Copy(docLabels, 0, windowLabels, 0, windowLabels.Length);
// shift the docLabels array left
int[] newDocLabels = new int[docData.Length];
System.Array.Copy(docLabels, docLabels.Length - newDocLabels.Length, newDocLabels, 0, newDocLabels.Length);
docLabels = newDocLabels;
}
for (int i = 0; i < docData.Length; i++)
{
System.Array.Copy(windowLabels, 1, windowLabels, 0, window - 1);
windowLabels[window - 1] = docLabels[i];
int[][] docDataI = docData[i];
for (int j = 0; j < docDataI.Length; j++)
{
// j iterates over cliques
int[] docDataIJ = docDataI[j];
int[] cliqueLabel = new int[j + 1];
System.Array.Copy(windowLabels, window - 1 - j, cliqueLabel, 0, j + 1);
CRFLabel crfLabel = new CRFLabel(cliqueLabel);
IIndex <CRFLabel> labelIndex = labelIndices[j];
int observedLabelIndex = labelIndex.IndexOf(crfLabel);
//log.info(crfLabel + " " + observedLabelIndex);
for (int lopIter = 0; lopIter < numLopExpert; lopIter++)
{
double[][] ehatOfIter = Ehat[lopIter];
ICollection <int> indicesSet = featureIndicesSetArray[lopIter];
foreach (int featureIdx in docDataIJ)
{
// k iterates over features
if (indicesSet.Contains(featureIdx))
{
ehatOfIter[featureIdx][observedLabelIndex]++;
}
}
}
}
}
}
}
protected internal virtual void EmpiricalCountsForADoc(double[][] eHat, int docIndex)
{
int[][][] docData = data[docIndex];
int[] docLabels = labels[docIndex];
int[] windowLabels = new int[window];
Arrays.Fill(windowLabels, classIndex.IndexOf(backgroundSymbol));
double[][][] featureValArr = null;
if (featureVal != null)
{
featureValArr = featureVal[docIndex];
}
if (docLabels.Length > docData.Length)
{
// only true for self-training
// fill the windowLabel array with the extra docLabels
System.Array.Copy(docLabels, 0, windowLabels, 0, windowLabels.Length);
// shift the docLabels array left
int[] newDocLabels = new int[docData.Length];
System.Array.Copy(docLabels, docLabels.Length - newDocLabels.Length, newDocLabels, 0, newDocLabels.Length);
docLabels = newDocLabels;
}
for (int i = 0; i < docData.Length; i++)
{
System.Array.Copy(windowLabels, 1, windowLabels, 0, window - 1);
windowLabels[window - 1] = docLabels[i];
for (int j = 0; j < docData[i].Length; j++)
{
int[] cliqueLabel = new int[j + 1];
System.Array.Copy(windowLabels, window - 1 - j, cliqueLabel, 0, j + 1);
CRFLabel crfLabel = new CRFLabel(cliqueLabel);
int labelIndex = labelIndices[j].IndexOf(crfLabel);
//log.info(crfLabel + " " + labelIndex);
for (int n = 0; n < docData[i][j].Length; n++)
{
double fVal = 1.0;
if (featureValArr != null && j == 0)
{
// j == 0 because only node features gets feature values
fVal = featureValArr[i][j][n];
}
eHat[docData[i][j][n]][labelIndex] += fVal;
}
}
}
}
// todo [cdm]: Below data[m] --> docData
/// <summary>Calculates both value and partial derivatives at the point x, and save them internally.</summary>
protected internal override void Calculate(double[] x)
{
double prob = 0.0;
// the log prob of the sequence given the model, which is the negation of value at this point
Quadruple <double[][], double[][], double[][], double[][]> allParams = SeparateWeights(x);
double[][] W4Edge = allParams.First();
// inputLayerWeights4Edge
double[][] U4Edge = allParams.Second();
// outputLayerWeights4Edge
double[][] W = allParams.Third();
// inputLayerWeights
double[][] U = allParams.Fourth();
// outputLayerWeights
double[][] Y4Edge = null;
double[][] Y = null;
if (flags.softmaxOutputLayer)
{
Y4Edge = new double[U4Edge.Length][];
for (int i = 0; i < U4Edge.Length; i++)
{
Y4Edge[i] = ArrayMath.Softmax(U4Edge[i]);
}
Y = new double[U.Length][];
for (int i_1 = 0; i_1 < U.Length; i_1++)
{
Y[i_1] = ArrayMath.Softmax(U[i_1]);
}
}
double[][] What4Edge = EmptyW4Edge();
double[][] Uhat4Edge = EmptyU4Edge();
double[][] What = EmptyW();
double[][] Uhat = EmptyU();
// the expectations over counts
// first index is feature index, second index is of possible labeling
double[][] eW4Edge = EmptyW4Edge();
double[][] eU4Edge = EmptyU4Edge();
double[][] eW = EmptyW();
double[][] eU = EmptyU();
// iterate over all the documents
for (int m = 0; m < data.Length; m++)
{
int[][][] docData = data[m];
int[] docLabels = labels[m];
NonLinearSecondOrderCliquePotentialFunction cliquePotentialFunction = new NonLinearSecondOrderCliquePotentialFunction(W4Edge, U4Edge, W, U, flags);
// make a clique tree for this document
CRFCliqueTree <string> cliqueTree = CRFCliqueTree.GetCalibratedCliqueTree(docData, labelIndices, numClasses, classIndex, backgroundSymbol, cliquePotentialFunction, null);
// compute the log probability of the document given the model with the parameters x
int[] given = new int[window - 1];
Arrays.Fill(given, classIndex.IndexOf(backgroundSymbol));
int[] windowLabels = new int[window];
Arrays.Fill(windowLabels, classIndex.IndexOf(backgroundSymbol));
if (docLabels.Length > docData.Length)
{
// only true for self-training
// fill the given array with the extra docLabels
System.Array.Copy(docLabels, 0, given, 0, given.Length);
System.Array.Copy(docLabels, 0, windowLabels, 0, windowLabels.Length);
// shift the docLabels array left
int[] newDocLabels = new int[docData.Length];
System.Array.Copy(docLabels, docLabels.Length - newDocLabels.Length, newDocLabels, 0, newDocLabels.Length);
docLabels = newDocLabels;
}
// iterate over the positions in this document
for (int i = 0; i < docData.Length; i++)
{
int label = docLabels[i];
double p = cliqueTree.CondLogProbGivenPrevious(i, label, given);
if (Verbose)
{
log.Info("P(" + label + "|" + ArrayMath.ToString(given) + ")=" + p);
}
prob += p;
System.Array.Copy(given, 1, given, 0, given.Length - 1);
given[given.Length - 1] = label;
}
// compute the expected counts for this document, which we will need to compute the derivative
// iterate over the positions in this document
for (int i_1 = 0; i_1 < docData.Length; i_1++)
{
// for each possible clique at this position
System.Array.Copy(windowLabels, 1, windowLabels, 0, window - 1);
windowLabels[window - 1] = docLabels[i_1];
for (int j = 0; j < docData[i_1].Length; j++)
{
IIndex <CRFLabel> labelIndex = labelIndices[j];
// for each possible labeling for that clique
int[] cliqueFeatures = docData[i_1][j];
double[] As = null;
double[] fDeriv = null;
double[][] yTimesA = null;
double[] sumOfYTimesA = null;
int inputSize;
int outputSize = -1;
if (j == 0)
{
inputSize = inputLayerSize;
outputSize = outputLayerSize;
As = cliquePotentialFunction.HiddenLayerOutput(W, cliqueFeatures, flags, null, j + 1);
}
else
{
inputSize = inputLayerSize4Edge;
outputSize = outputLayerSize4Edge;
As = cliquePotentialFunction.HiddenLayerOutput(W4Edge, cliqueFeatures, flags, null, j + 1);
}
fDeriv = new double[inputSize];
double fD = 0;
for (int q = 0; q < inputSize; q++)
{
if (useSigmoid)
{
fD = As[q] * (1 - As[q]);
}
else
{
fD = 1 - As[q] * As[q];
}
fDeriv[q] = fD;
}
// calculating yTimesA for softmax
if (flags.softmaxOutputLayer)
{
double val = 0;
yTimesA = new double[outputSize][];
for (int ii = 0; ii < outputSize; ii++)
{
yTimesA[ii] = new double[numHiddenUnits];
}
sumOfYTimesA = new double[outputSize];
for (int k = 0; k < outputSize; k++)
{
double[] Yk = null;
if (flags.tieOutputLayer)
{
if (j == 0)
{
Yk = Y[0];
}
else
{
Yk = Y4Edge[0];
}
}
else
{
if (j == 0)
{
Yk = Y[k];
}
else
{
Yk = Y4Edge[k];
}
}
double sum = 0;
for (int q_1 = 0; q_1 < inputSize; q_1++)
{
if (q_1 % outputSize == k)
{
int hiddenUnitNo = q_1 / outputSize;
val = As[q_1] * Yk[hiddenUnitNo];
yTimesA[k][hiddenUnitNo] = val;
sum += val;
}
}
sumOfYTimesA[k] = sum;
}
}
// calculating Uhat What
int[] cliqueLabel = new int[j + 1];
System.Array.Copy(windowLabels, window - 1 - j, cliqueLabel, 0, j + 1);
CRFLabel crfLabel = new CRFLabel(cliqueLabel);
int givenLabelIndex = labelIndex.IndexOf(crfLabel);
double[] Uk = null;
double[] UhatK = null;
double[] Yk_1 = null;
double[] yTimesAK = null;
double sumOfYTimesAK = 0;
if (flags.tieOutputLayer)
{
if (j == 0)
{
Uk = U[0];
UhatK = Uhat[0];
}
else
{
Uk = U4Edge[0];
UhatK = Uhat4Edge[0];
}
if (flags.softmaxOutputLayer)
{
if (j == 0)
{
Yk_1 = Y[0];
}
else
{
Yk_1 = Y4Edge[0];
}
}
}
else
{
if (j == 0)
{
Uk = U[givenLabelIndex];
UhatK = Uhat[givenLabelIndex];
}
else
{
Uk = U4Edge[givenLabelIndex];
UhatK = Uhat4Edge[givenLabelIndex];
}
if (flags.softmaxOutputLayer)
{
if (j == 0)
{
Yk_1 = Y[givenLabelIndex];
}
else
{
Yk_1 = Y4Edge[givenLabelIndex];
}
}
}
if (flags.softmaxOutputLayer)
{
yTimesAK = yTimesA[givenLabelIndex];
sumOfYTimesAK = sumOfYTimesA[givenLabelIndex];
}
for (int k_1 = 0; k_1 < inputSize; k_1++)
{
double deltaK = 1;
if (flags.sparseOutputLayer || flags.tieOutputLayer)
{
if (k_1 % outputSize == givenLabelIndex)
{
int hiddenUnitNo = k_1 / outputSize;
if (flags.softmaxOutputLayer)
{
UhatK[hiddenUnitNo] += (yTimesAK[hiddenUnitNo] - Yk_1[hiddenUnitNo] * sumOfYTimesAK);
deltaK *= Yk_1[hiddenUnitNo];
}
else
{
UhatK[hiddenUnitNo] += As[k_1];
deltaK *= Uk[hiddenUnitNo];
}
}
}
else
{
UhatK[k_1] += As[k_1];
if (useOutputLayer)
{
deltaK *= Uk[k_1];
}
}
if (useHiddenLayer)
{
deltaK *= fDeriv[k_1];
}
if (useOutputLayer)
{
if (flags.sparseOutputLayer || flags.tieOutputLayer)
{
if (k_1 % outputSize == givenLabelIndex)
{
double[] WhatK = null;
if (j == 0)
{
WhatK = What[k_1];
}
else
{
WhatK = What4Edge[k_1];
}
foreach (int cliqueFeature in cliqueFeatures)
{
WhatK[cliqueFeature] += deltaK;
}
}
}
else
{
double[] WhatK = null;
if (j == 0)
{
WhatK = What[k_1];
}
else
{
WhatK = What4Edge[k_1];
}
foreach (int cliqueFeature in cliqueFeatures)
{
WhatK[cliqueFeature] += deltaK;
}
}
}
else
{
if (k_1 == givenLabelIndex)
{
double[] WhatK = null;
if (j == 0)
{
WhatK = What[k_1];
}
else
{
WhatK = What4Edge[k_1];
}
foreach (int cliqueFeature in cliqueFeatures)
{
WhatK[cliqueFeature] += deltaK;
}
}
}
}
for (int k_2 = 0; k_2 < labelIndex.Size(); k_2++)
{
// labelIndex.size() == numClasses
int[] label = labelIndex.Get(k_2).GetLabel();
double p = cliqueTree.Prob(i_1, label);
// probability of these labels occurring in this clique with these features
double[] Uk2 = null;
double[] eUK = null;
double[] Yk2 = null;
if (flags.tieOutputLayer)
{
if (j == 0)
{
// for node features
Uk2 = U[0];
eUK = eU[0];
}
else
{
Uk2 = U4Edge[0];
eUK = eU4Edge[0];
}
if (flags.softmaxOutputLayer)
{
if (j == 0)
{
Yk2 = Y[0];
}
else
{
Yk2 = Y4Edge[0];
}
}
}
else
{
if (j == 0)
{
Uk2 = U[k_2];
eUK = eU[k_2];
}
else
{
Uk2 = U4Edge[k_2];
eUK = eU4Edge[k_2];
}
if (flags.softmaxOutputLayer)
{
if (j == 0)
{
Yk2 = Y[k_2];
}
else
{
Yk2 = Y4Edge[k_2];
}
}
}
if (useOutputLayer)
{
for (int q_1 = 0; q_1 < inputSize; q_1++)
{
double deltaQ = 1;
if (flags.sparseOutputLayer || flags.tieOutputLayer)
{
if (q_1 % outputSize == k_2)
{
int hiddenUnitNo = q_1 / outputSize;
if (flags.softmaxOutputLayer)
{
eUK[hiddenUnitNo] += (yTimesA[k_2][hiddenUnitNo] - Yk2[hiddenUnitNo] * sumOfYTimesA[k_2]) * p;
deltaQ = Yk2[hiddenUnitNo];
}
else
{
eUK[hiddenUnitNo] += As[q_1] * p;
deltaQ = Uk2[hiddenUnitNo];
}
}
}
else
{
eUK[q_1] += As[q_1] * p;
deltaQ = Uk2[q_1];
}
if (useHiddenLayer)
{
deltaQ *= fDeriv[q_1];
}
if (flags.sparseOutputLayer || flags.tieOutputLayer)
{
if (q_1 % outputSize == k_2)
{
double[] eWq = null;
if (j == 0)
{
eWq = eW[q_1];
}
else
{
eWq = eW4Edge[q_1];
}
foreach (int cliqueFeature in cliqueFeatures)
{
eWq[cliqueFeature] += deltaQ * p;
}
}
}
else
{
double[] eWq = null;
if (j == 0)
{
eWq = eW[q_1];
}
else
{
eWq = eW4Edge[q_1];
}
foreach (int cliqueFeature in cliqueFeatures)
{
eWq[cliqueFeature] += deltaQ * p;
}
}
}
}
else
{
double deltaK = 1;
if (useHiddenLayer)
{
deltaK *= fDeriv[k_2];
}
double[] eWK = null;
if (j == 0)
{
eWK = eW[k_2];
}
else
{
eWK = eW4Edge[k_2];
}
foreach (int cliqueFeature in cliqueFeatures)
{
eWK[cliqueFeature] += deltaK * p;
}
}
}
}
}
}
if (double.IsNaN(prob))
{
// shouldn't be the case
throw new Exception("Got NaN for prob in CRFNonLinearSecondOrderLogConditionalObjectiveFunction.calculate()");
}
value = -prob;
if (Verbose)
{
log.Info("value is " + value);
}
// compute the partial derivative for each feature by comparing expected counts to empirical counts
int index = 0;
for (int i_2 = 0; i_2 < eW4Edge.Length; i_2++)
{
for (int j = 0; j < eW4Edge[i_2].Length; j++)
{
derivative[index++] = (eW4Edge[i_2][j] - What4Edge[i_2][j]);
if (Verbose)
{
log.Info("inputLayerWeights4Edge deriv(" + i_2 + "," + j + ") = " + eW4Edge[i_2][j] + " - " + What4Edge[i_2][j] + " = " + derivative[index - 1]);
}
}
}
for (int i_3 = 0; i_3 < eW.Length; i_3++)
{
for (int j = 0; j < eW[i_3].Length; j++)
{
derivative[index++] = (eW[i_3][j] - What[i_3][j]);
if (Verbose)
{
log.Info("inputLayerWeights deriv(" + i_3 + "," + j + ") = " + eW[i_3][j] + " - " + What[i_3][j] + " = " + derivative[index - 1]);
}
}
}
if (index != beforeOutputWeights)
{
throw new Exception("after W derivative, index(" + index + ") != beforeOutputWeights(" + beforeOutputWeights + ")");
}
if (useOutputLayer)
{
for (int i = 0; i_3 < eU4Edge.Length; i_3++)
{
for (int j = 0; j < eU4Edge[i_3].Length; j++)
{
derivative[index++] = (eU4Edge[i_3][j] - Uhat4Edge[i_3][j]);
if (Verbose)
{
log.Info("outputLayerWeights4Edge deriv(" + i_3 + "," + j + ") = " + eU4Edge[i_3][j] + " - " + Uhat4Edge[i_3][j] + " = " + derivative[index - 1]);
}
}
}
for (int i_1 = 0; i_1 < eU.Length; i_1++)
{
for (int j = 0; j < eU[i_1].Length; j++)
{
derivative[index++] = (eU[i_1][j] - Uhat[i_1][j]);
if (Verbose)
{
log.Info("outputLayerWeights deriv(" + i_1 + "," + j + ") = " + eU[i_1][j] + " - " + Uhat[i_1][j] + " = " + derivative[index - 1]);
}
}
}
}
if (index != x.Length)
{
throw new Exception("after W derivative, index(" + index + ") != x.length(" + x.Length + ")");
}
int regSize = x.Length;
if (flags.skipOutputRegularization || flags.softmaxOutputLayer)
{
regSize = beforeOutputWeights;
}
// incorporate priors
if (prior == QuadraticPrior)
{
double sigmaSq = sigma * sigma;
for (int i = 0; i_3 < regSize; i_3++)
{
double k = 1.0;
double w = x[i_3];
value += k * w * w / 2.0 / sigmaSq;
derivative[i_3] += k * w / sigmaSq;
}
}
else
{
if (prior == HuberPrior)
{
double sigmaSq = sigma * sigma;
for (int i = 0; i_3 < regSize; i_3++)
{
double w = x[i_3];
double wabs = System.Math.Abs(w);
if (wabs < epsilon)
{
value += w * w / 2.0 / epsilon / sigmaSq;
derivative[i_3] += w / epsilon / sigmaSq;
}
else
{
value += (wabs - epsilon / 2) / sigmaSq;
derivative[i_3] += ((w < 0.0) ? -1.0 : 1.0) / sigmaSq;
}
}
}
else
{
if (prior == QuarticPrior)
{
double sigmaQu = sigma * sigma * sigma * sigma;
for (int i = 0; i_3 < regSize; i_3++)
{
double k = 1.0;
double w = x[i_3];
value += k * w * w * w * w / 2.0 / sigmaQu;
derivative[i_3] += k * w / sigmaQu;
}
}
}
}
}
public virtual void CalculateWeird1(float[] x)
{
float[][] weights = To2D(x);
float[][] E = Empty2D();
value = 0.0f;
Arrays.Fill(derivative, 0.0f);
float[][] sums = new float[labelIndices.Count][];
float[][] probs = new float[labelIndices.Count][];
float[][] counts = new float[labelIndices.Count][];
for (int i = 0; i < sums.Length; i++)
{
int size = labelIndices[i].Size();
sums[i] = new float[size];
probs[i] = new float[size];
counts[i] = new float[size];
}
// Arrays.fill(counts[i], 0.0f); // not needed; Java arrays zero initialized
for (int d = 0; d < data.Length; d++)
{
int[] llabels = labels[d];
for (int e = 0; e < data[d].Length; e++)
{
int[][] ddata = this.data[d][e];
for (int cl = 0; cl < ddata.Length; cl++)
{
int[] features = ddata[cl];
// activation
Arrays.Fill(sums[cl], 0.0f);
int numClasses = labelIndices[cl].Size();
for (int c = 0; c < numClasses; c++)
{
foreach (int feature in features)
{
sums[cl][c] += weights[feature][c];
}
}
}
for (int cl_1 = 0; cl_1 < ddata.Length; cl_1++)
{
int[] label = new int[cl_1 + 1];
//Arrays.fill(label, classIndex.indexOf("O"));
Arrays.Fill(label, classIndex.IndexOf(backgroundSymbol));
int index1 = label.Length - 1;
for (int pos = e; pos >= 0 && index1 >= 0; pos--)
{
//log.info(index1+" "+pos);
label[index1--] = llabels[pos];
}
CRFLabel crfLabel = new CRFLabel(label);
int labelIndex = labelIndices[cl_1].IndexOf(crfLabel);
float total = ArrayMath.LogSum(sums[cl_1]);
// int[] features = ddata[cl];
int numClasses = labelIndices[cl_1].Size();
for (int c = 0; c < numClasses; c++)
{
probs[cl_1][c] = (float)System.Math.Exp(sums[cl_1][c] - total);
}
// for (int f=0; f<features.length; f++) {
// for (int c=0; c<numClasses; c++) {
// //probs[cl][c] = Math.exp(sums[cl][c]-total);
// derivative[index] += probs[cl][c];
// if (c == labelIndex) {
// derivative[index]--;
// }
// index++;
// }
// }
value -= sums[cl_1][labelIndex] - total;
}
// // observed
// for (int f=0; f<features.length; f++) {
// //int i = indexOf(features[f], labels[d]);
// derivative[index+labelIndex] -= 1.0;
// }
// go through each clique...
for (int j = 0; j < data[d][e].Length; j++)
{
IIndex <CRFLabel> labelIndex = labelIndices[j];
// ...and each possible labeling for that clique
for (int k = 0; k < labelIndex.Size(); k++)
{
//int[] label = ((CRFLabel) labelIndex.get(k)).getLabel();
// float p = Math.pow(Math.E, factorTables[i].logProbEnd(label));
float p = probs[j][k];
for (int n = 0; n < data[d][e][j].Length; n++)
{
E[data[d][e][j][n]][k] += p;
}
}
}
}
}
// compute the partial derivative for each feature
int index = 0;
for (int i_1 = 0; i_1 < E.Length; i_1++)
{
for (int j = 0; j < E[i_1].Length; j++)
{
derivative[index++] = (E[i_1][j] - Ehat[i_1][j]);
}
}
// observed
// int index = 0;
// for (int i = 0; i < Ehat.length; i++) {
// for (int j = 0; j < Ehat[i].length; j++) {
// derivative[index++] -= Ehat[i][j];
// }
// }
// priors
if (prior == QuadraticPrior)
{
float sigmaSq = sigma * sigma;
for (int i_2 = 0; i_2 < x.Length; i_2++)
{
float k = 1.0f;
float w = x[i_2];
value += k * w * w / 2.0 / sigmaSq;
derivative[i_2] += k * w / sigmaSq;
}
}
else
{
if (prior == HuberPrior)
{
float sigmaSq = sigma * sigma;
for (int i_2 = 0; i_2 < x.Length; i_2++)
{
float w = x[i_2];
float wabs = System.Math.Abs(w);
if (wabs < epsilon)
{
value += w * w / 2.0 / epsilon / sigmaSq;
derivative[i_2] += w / epsilon / sigmaSq;
}
else
{
value += (wabs - epsilon / 2) / sigmaSq;
derivative[i_2] += ((w < 0.0) ? -1.0 : 1.0) / sigmaSq;
}
}
}
else
{
if (prior == QuarticPrior)
{
float sigmaQu = sigma * sigma * sigma * sigma;
for (int i_2 = 0; i_2 < x.Length; i_2++)
{
float k = 1.0f;
float w = x[i_2];
value += k * w * w * w * w / 2.0 / sigmaQu;
derivative[i_2] += k * w / sigmaQu;
}
}
}
}
}
private void LogPotential(double[][][] learnedLopExpertWeights2D)
{
sumOfExpectedLogPotential = new double[data.Length][][][][];
sumOfObservedLogPotential = new double[numLopExpert];
for (int m = 0; m < data.Length; m++)
{
int[][][] docData = data[m];
int[] docLabels = labels[m];
int[] windowLabels = new int[window];
Arrays.Fill(windowLabels, classIndex.IndexOf(backgroundSymbol));
double[][][][] sumOfELPm = new double[docData.Length][][][];
if (docLabels.Length > docData.Length)
{
// only true for self-training
// fill the windowLabel array with the extra docLabels
System.Array.Copy(docLabels, 0, windowLabels, 0, windowLabels.Length);
// shift the docLabels array left
int[] newDocLabels = new int[docData.Length];
System.Array.Copy(docLabels, docLabels.Length - newDocLabels.Length, newDocLabels, 0, newDocLabels.Length);
docLabels = newDocLabels;
}
for (int i = 0; i < docData.Length; i++)
{
System.Array.Copy(windowLabels, 1, windowLabels, 0, window - 1);
windowLabels[window - 1] = docLabels[i];
double[][][] sumOfELPmi = new double[docData[i].Length][][];
int[][] docDataI = docData[i];
for (int j = 0; j < docDataI.Length; j++)
{
// j iterates over cliques
int[] docDataIJ = docDataI[j];
int[] cliqueLabel = new int[j + 1];
System.Array.Copy(windowLabels, window - 1 - j, cliqueLabel, 0, j + 1);
CRFLabel crfLabel = new CRFLabel(cliqueLabel);
IIndex <CRFLabel> labelIndex = labelIndices[j];
double[][] sumOfELPmij = new double[numLopExpert][];
int observedLabelIndex = labelIndex.IndexOf(crfLabel);
//log.info(crfLabel + " " + observedLabelIndex);
for (int lopIter = 0; lopIter < numLopExpert; lopIter++)
{
double[] sumOfELPmijIter = new double[labelIndex.Size()];
ICollection <int> indicesSet = featureIndicesSetArray[lopIter];
foreach (int featureIdx in docDataIJ)
{
// k iterates over features
if (indicesSet.Contains(featureIdx))
{
sumOfObservedLogPotential[lopIter] += learnedLopExpertWeights2D[lopIter][featureIdx][observedLabelIndex];
// sum over potential of this clique over all possible labels, used later in calculating expected counts
for (int l = 0; l < labelIndex.Size(); l++)
{
sumOfELPmijIter[l] += learnedLopExpertWeights2D[lopIter][featureIdx][l];
}
}
}
sumOfELPmij[lopIter] = sumOfELPmijIter;
}
sumOfELPmi[j] = sumOfELPmij;
}
sumOfELPm[i] = sumOfELPmi;
}
sumOfExpectedLogPotential[m] = sumOfELPm;
}
}
