[release-notes] SHOGUN machine learning toolkit

[Pete Travis]

commit d25bf73d2c9eab958942f308afd9c76a535f8483
Author: Pete Travis <immanetize at fedoraproject.org>
Date:   Thu Oct 9 23:07:48 2014 -0600

    SHOGUN machine learning toolkit

 en-US/Development_Tools.xml |   14 +++++++++++++-
 1 files changed, 13 insertions(+), 1 deletions(-)
---
diff --git a/en-US/Development_Tools.xml b/en-US/Development_Tools.xml
index 543bfb5..3e33e81 100644
--- a/en-US/Development_Tools.xml
+++ b/en-US/Development_Tools.xml
@@ -61,6 +61,18 @@
       </para>
     </important>
   </section>
-
+  <section id="devtools-shogun">
+    <title>SHOGUN Machine Learning Toolbox</title>
+    <para>
+      The machine learning toolbox's focus is on large scale kernel methods and especially on <ulink url="http://en.wikipedia.org/wiki/Support_vector_machine">Support Vector Machines (SVM)</ulink>. It provides a generic SVM object interfacing to several different SVM implementations, among them the state of the art <ulink url="http://en.wikipedia.org/wiki/LIBSVM">LibSVM</ulink>. Each of the SVMs can be combined with a variety of kernels.
+    </para>
+    <para>
+      One of its key features is the "combined kernel" which can be constructed by a weighted linear combination of a number of sub-kernels, each of which not necessarily working on the same domain. An optimal sub-kernel weighting can be learned using Multiple Kernel Learning. Currently SVM 2-class classification and regression problems can be dealt with. However SHOGUN also implements a number of linear methods like Linear Discriminant Analysis (LDA), Linear Programming Machine (LPM), (Kernel) Perceptrons and features algorithms to train hidden Markov-models. 
+    </para>
+    <para>
+      Learn more about <package>SHOGUN</package> at <ulink url="http://shogun-toolbox.org/doc/en/current/" />
+    </para>
+  </section>
+      
 </section>