The library contains a number of interconnected Java packages that implement machine learning and artificial intelligence algorithms. These are artificial intelligence algorithms implemented for the kind of people that like to implement algorithms themselves.

*For discrete optimization problems see java examples /src/opt/test or jython versions /jython
*For jython | csv | python and grid search examples see /jython
*Also see Wiki, FAQ

Here is a simple example of how to import data and build a neural network using the iris data set (taken from IrisTest.java). Train and test error will be exported in csv format to the current working directory.

//import data
DataSetReader dsr = new CSVDataSetReader((new File("src/opt/test/iris.txt")).getAbsolutePath());
DataSet ds = dsr.read();

//split last attribute for label
LabelSplitFilter lsf = new LabelSplitFilter();
lsf.filter(ds);

//encode label as one-hot array and get outputLayerSize
DiscreteToBinaryFilter dbf = new DiscreteToBinaryFilter();
dbf.filter(ds.getLabelDataSet());
outputLayerSize=dbf.getNewAttributeCount();

//test-train split
int percentTrain=75;
RandomOrderFilter randomOrderFilter = new RandomOrderFilter();
randomOrderFilter.filter(ds);
TestTrainSplitFilter testTrainSplit = new TestTrainSplitFilter(percentTrain);
testTrainSplit.filter(ds);
train=testTrainSplit.getTrainingSet();
test=testTrainSplit.getTestingSet();

//standardize data
StandardMeanAndVariance smv = new StandardMeanAndVariance();
smv.fit(train);
smv.transform(train);
smv.transform(test);

//create backprop network using builder
BackPropagationNetwork network = new BackpropNetworkBuilder()
  .withLayers(new int[] {25,10,outputLayerSize})
  .withDataSet(train, test)
  .withIterations(5000)
  .train();
  
//create opt network using builder
FeedForwardNetwork optNetwork = new OptNetworkBuilder()
  .withLayers(new int[] {25,10,outputLayerSize})
  .withDataSet(train, test)
  .withSA(100000, .975)
  .withIterations(1000)
  .train();

1. Fork it.
2. Create a branch (git checkout -b my_branch)
3. Commit your changes (git commit -am "Awesome feature")
4. Push to the branch (git push origin my_branch)
5. Open a Pull Request
6. Enjoy a refreshing Diet Coke and wait

• Baum-Welch reestimation algorithm, scaled forward-backward algorithm, Viterbi algorithm
• Support for Input-Output Hidden Markov Models
• Write your own output or transition probability distribution or use the provided distributions, including neural network based conditional probability distributions
• Neural Networks

• Configurable error functions with sum of squares, weighted sum of squares
• Multiple activation functions with logistic sigmoid, linear, tanh, and soft max
• Choose your weight update rule with standard update rule, standard update rule with momentum, Quickprop, RPROP
• Online and batch training
• Support Vector Machines

• Support for linear, polynomial, tanh, radial basis function kernels
• Decision Trees

• Binary or all attribute value splitting
• Chi-square signifigance test pruning with configurable confidence levels
• Boosted decision stumps with AdaBoost
• K Nearest Neighbors

• KNN Classifier with weighted or non-weighted classification, customizable distance function
• Linear Algebra Algorithms

• Solve square systems, upper triangular systems, lower triangular systems, least squares
• Singular Value Decomposition, QR Decomposition, LU Decomposition, Schur Decomposition, Symmetric Eigenvalue Decomposition, Cholesky Factorization
• Make your own matrix decomposition with the easy to use Householder Reflection and Givens Rotation classes
• Optimization Algorithms

• Make your own crossover functions, mutation functions, neighbor functions, probability distributions, or use the provided ones.
• Optimize the weights of neural networks and solve travelling salesman problems
• Graph Algorithms

• Clustering Algorithms

• Data Preprocessing

• Convert from continuous to discrete, discrete to binary
• Reinforcement Learning