diff options
author | cheusov <cheusov@pkgsrc.org> | 2016-07-30 15:13:57 +0000 |
---|---|---|
committer | cheusov <cheusov@pkgsrc.org> | 2016-07-30 15:13:57 +0000 |
commit | 12dbd510a8e00d0256f8123092ab1fe091caa6af (patch) | |
tree | 79955d2cbaf9613aeee119fc5a7cd7b2b348a0ea /math/svmlin/DESCR | |
parent | 4bf565f5d2fadf5833b687cc16e4684cb4ed2f51 (diff) | |
download | pkgsrc-12dbd510a8e00d0256f8123092ab1fe091caa6af.tar.gz |
Import svmlin, semi-supervised machine learning tool
Diffstat (limited to 'math/svmlin/DESCR')
-rw-r--r-- | math/svmlin/DESCR | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/math/svmlin/DESCR b/math/svmlin/DESCR new file mode 100644 index 00000000000..946d6e73103 --- /dev/null +++ b/math/svmlin/DESCR @@ -0,0 +1,15 @@ +SVMlin is software package for linear SVMs. It is well-suited to +classification problems involving a large number of examples and features. +It is primarily written for sparse datasets. + +SVMlin can also utilize unlabeled data, in addition to labeled examples. +It currently implements two extensions of standard SVMs to incorporate +unlabeled examples. + +SVMlin implements the following algorithms: + - Fully supervised [using only labeled examples] + * Linear Regularized Least Squares (RLS) Classification + * Modified Finite Newton Linear L2-SVMs + - Semi-supervised [can use unlabeled data as well] + * Linear Transductive L2-SVMs with multiple switchings + * Deterministic Annealing (DA) for Semi-supervised Linear L2-SVMs |