public CrossFoldLearner alpha(double alpha) { for (OnlineLogisticRegression model : models) { model.alpha(alpha); } return this; }
public CrossFoldLearner alpha(double alpha) { for (OnlineLogisticRegression model : models) { model.alpha(alpha); } return this; }
public CrossFoldLearner alpha(double alpha) { for (OnlineLogisticRegression model : models) { model.alpha(alpha); } return this; }
public CrossFoldLearner(int folds, int numCategories, int numFeatures, PriorFunction prior) { this.numFeatures = numFeatures; this.prior = prior; for (int i = 0; i < folds; i++) { OnlineLogisticRegression model = new OnlineLogisticRegression(numCategories, numFeatures, prior); model.alpha(1).stepOffset(0).decayExponent(0); models.add(model); } }
public CrossFoldLearner(int folds, int numCategories, int numFeatures, PriorFunction prior) { this.numFeatures = numFeatures; this.prior = prior; for (int i = 0; i < folds; i++) { OnlineLogisticRegression model = new OnlineLogisticRegression(numCategories, numFeatures, prior); model.alpha(1).stepOffset(0).decayExponent(0); models.add(model); } }
public CrossFoldLearner(int folds, int numCategories, int numFeatures, PriorFunction prior) { this.numFeatures = numFeatures; this.prior = prior; for (int i = 0; i < folds; i++) { OnlineLogisticRegression model = new OnlineLogisticRegression(numCategories, numFeatures, prior); model.alpha(1).stepOffset(0).decayExponent(0); models.add(model); } }
new OnlineLogisticRegression( 20, FEATURES, new L1()) .alpha(1).stepOffset(1000) .decayExponent(0.9) .lambda(3.0e-5)
.lambda(1 * 1.0e-3) .stepOffset(11) .alpha(0.01) .learningRate(50) .decayExponent(-0.02);