A new version of kernlab has just been released.
kernlab is a kernel-based Machine Learning package for R.
kernlab includes the following functions:
o ksvm() : Support Vector Machines for classification, regression,
novelty detection, native multi-class classification, support
for class-probability output and confidence intervals in
regression.
o gausspr() : Gaussian Processes for classification and regression
o lssvm() : Least Squares Support Vector Machines for classification
o rvm() : Relevance Vector Machines for regression
o specc() : Spectral Clustering
o kkmeans() : Kernel k-means clustering
o ranking() : Kernel-based ranking method
o onlearn() : Kernel-based Online Learning algorithms for classification,
novelty detection and regression
o kpca() : Kernel Pricipal Components Analysis
o kcca() : Kernel Canonical Correlation Analysis
o kfa() : Kernel Feature Analysis
o sigest() : Hyperparameter estimation for the Gaussian and the Laplacian
kernels
o inchol() : Incomplete Cholesky decomposition method
o csi() : Cholesky decomposition with side information
o ipop() : Interior point-based Quadratic Optimizer
Kernlab also includes a range of functions enabling the easy implementation of
new kernel methods including functions for computing commonly used kernel
expressions (e.g. kernel matrix, kernel expansion, etc.) and
implementations of nine kernels (e.g. Linear, Gaussian, Polynomial,
Sigmoid, Laplace, String kernels, etc.) which can be used with any of the
functions included in the package.
Ready computed kernel matrices and user defined kernel functions can also
be used.
kernlab is based on the S4 object model.
A vignette describing a large portion of the functions and features is
included.
cheers
Alexandros
_______________________________________________
R-packages mailing list
R-packages at stat.math.ethz.ch
https://stat.ethz.ch/mailman/listinfo/r-packages
