Changeset 14837 for branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAlgorithm.cs

Timestamp:

04/10/17 15:50:16 (8 years ago)

Author:

gkronber

Message:

#2700 made some changes while reviewing (comparsion with bh_tsne implementation by van der Maarten)

File:

• branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAlgorithm.cs (modified) (3 diffs)

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/TSNEAlgorithm.cs

@@ -200 +200 @@
       Parameters.Add(new ValueParameter<IDistance<double[]>>(DistanceParameterName, "The distance function used to differentiate similar from non-similar points", new EuclideanDistance()));
       Parameters.Add(new FixedValueParameter<DoubleValue>(PerplexityParameterName, "Perplexity-parameter of tSNE. Comparable to k in a k-nearest neighbour algorithm. Recommended value is floor(number of points /3) or lower", new DoubleValue(25)));
-      Parameters.Add(new FixedValueParameter<DoubleValue>(ThetaParameterName, "Value describing how much appoximated gradients my differ from exact gradients. Set to 0 for exact calculation and in [0,1] otherwise. CAUTION: exact calculation of forces requires building a non-sparse N*N matrix where N is the number of data points. This may exceed memory limitations.", new DoubleValue(0)));
+      Parameters.Add(new FixedValueParameter<DoubleValue>(ThetaParameterName, "Value describing how much appoximated " +
+                                                                              "gradients my differ from exact gradients. Set to 0 for exact calculation and in [0,1] otherwise. " +
+                                                                              "Appropriate values for theta are between 0.1 and 0.7 (default = 0.5). CAUTION: exact calculation of " +
+                                                                              "forces requires building a non-sparse N*N matrix where N is the number of data points. This may " +
+                                                                              "exceed memory limitations. The function is designed to run on large (N > 5000) data sets. It may give" +
+                                                                              " poor performance on very small data sets(it is better to use a standard t - SNE implementation on such data).", new DoubleValue(0)));
       Parameters.Add(new FixedValueParameter<IntValue>(NewDimensionsParameterName, "Dimensionality of projected space (usually 2 for easy visual analysis)", new IntValue(2)));
       Parameters.Add(new FixedValueParameter<IntValue>(MaxIterationsParameterName, "Maximum number of iterations for gradient descent.", new IntValue(1000)));
@@ -207 +212 @@
       Parameters.Add(new FixedValueParameter<DoubleValue>(InitialMomentumParameterName, "The initial momentum in the gradient descent.", new DoubleValue(0.5)));
       Parameters.Add(new FixedValueParameter<DoubleValue>(FinalMomentumParameterName, "The final momentum.", new DoubleValue(0.8)));
-      Parameters.Add(new FixedValueParameter<DoubleValue>(EtaParameterName, "Gradient descent learning rate.", new DoubleValue(200)));
+      Parameters.Add(new FixedValueParameter<DoubleValue>(EtaParameterName, "Gradient descent learning rate.", new DoubleValue(10)));
       Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "If the seed should be random.", new BoolValue(true)));
       Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The seed used if it should not be random.", new IntValue(0)));
@@ -217 +222 @@
       FinalMomentumParameter.Hidden = true;
       StopLyingIterationParameter.Hidden = true;
-      EtaParameter.Hidden = true;
+      EtaParameter.Hidden = false;
     }
     #endregion