Download JAR files tagged by optimization with all dependencies

RBFNetwork implements a normalized Gaussian radial basisbasis function network. It uses the k-means clustering algorithm to provide the basis functions and learns either a logistic regression (discrete class problems) or linear regression (numeric class problems) on top of that. Symmetric multivariate Gaussians are fit to the data from each cluster. If the class is nominal it uses the given number of clusters per class. RBFRegressor implements radial basis function networks for regression, trained in a fully supervised manner using WEKA's Optimization class by minimizing squared error with the BFGS method. It is possible to use conjugate gradient descent rather than BFGS updates, which is faster for cases with many parameters, and to use normalized basis functions instead of unnormalized ones.

A rigorous and well-sourced Java mathematics library that extends the Hipparchus mathematics library that includes linear algebra over R^n and C^n (e.g. Matrix, ComplexMatrix, Eigen, complex Schur using the M-shifted large-bulge QR alg., and complex QR and Hessenberg decompositions using Householder transformations), frameworks for and implementations of hyper-dimensional (N-dimensional) geometry (e.g., NOrthotope, NBall, RealNDomain, AbstractNDomain), weighted non-linear least-squares optimization (Levenmerg-Marquardt with geodesic acceleration), non-linear dynamics (e.g., DynamicalSystem, StateTransitionMatrix),and a rich framework of multi-variate, vector- and matrix-valued function definitions (e.g., MultivariateVectorValuedFunction, VectorField, MultivariateMatrixValuedFunction). Whenever a reference is used in the process of development, that source is included in the JavaDoc and, if possible, a hyperlink is provided.