From aa73c64c0429c69bae41ae74477fa247563cf909 Mon Sep 17 00:00:00 2001
From: Davis King <davis@dlib.net>
Date: Mon, 3 Jan 2011 20:46:26 +0000
Subject: [PATCH] updated docs

--HG--
extra : convert_revision : svn%3Afdd8eb12-d10e-0410-9acb-85c331704f74/trunk%404093
---
 docs/docs/index.xml         | 19 +++++++++-----
 docs/docs/release_notes.xml | 50 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 62 insertions(+), 7 deletions(-)

diff --git a/docs/docs/index.xml b/docs/docs/index.xml
index e782dec99..a1ae70bb3 100644
--- a/docs/docs/index.xml
+++ b/docs/docs/index.xml
@@ -103,15 +103,19 @@
                      <a href="dlib/matrix/matrix_la_abstract.h.html#svd">singular value decomposition</a>, 
                      <a href="dlib/matrix/matrix_utilities_abstract.h.html#trans">transpose</a>, 
                      <a href="dlib/matrix/matrix_math_functions_abstract.h.html#sin">trig functions</a>, etc.</li>
-                  <li>Unconstrained non-linear optimization algorithms using the  
+                  <li>General purpose unconstrained non-linear optimization algorithms using the  
                       <a href="optimization.html#cg_search_strategy">conjugate gradient</a>, 
-                      <a href="optimization.html#bfgs_search_strategy">BFGS</a>, 
-                      <a href="optimization.html#lbfgs_search_strategy">L-BFGS</a>, and
-                      <a href="optimization.html#solve_least_squares_lm">Levenberg-Marquardt</a>
+                      <a href="optimization.html#bfgs_search_strategy">BFGS</a>, and
+                      <a href="optimization.html#lbfgs_search_strategy">L-BFGS</a>
                       techniques</li>
+                  <li> <a href="optimization.html#solve_least_squares_lm">Levenberg-Marquardt</a> for solving non-linear
+                      least squares problems </li>
                   <li>Box-constrained derivative-free optimization via the 
                       <a href="optimization.html#find_min_bobyqa">BOBYQA</a> algorithm</li> 
                   <li>An implementation of the <a href="optimization.html#oca">Optimized Cutting Plane Algorithm</a></li> 
+                  <li>Several <a href="optimization.html#solve_qp2_using_smo">quadratic</a> 
+                              <a href="optimization.html#solve_qp3_using_smo">program</a> 
+                              <a href="optimization.html#solve_qp_using_smo">solvers</a> </li> 
                   <li>A <a href="algorithms.html#bigint">big integer</a> object</li>
                   <li>A <a href="algorithms.html#rand">random number</a> object</li>
                </ul>
@@ -119,14 +123,17 @@
 
             <li><b>Machine Learning Algorithms</b>
                <ul>
-                  <li>Conventional SMO based <a href="ml.html#svm_nu_trainer">Support vector machines</a> for classification</li>
+                  <li>Conventional SMO based Support Vector Machines for <a href="ml.html#svm_nu_trainer">classification</a> 
+                                                                    and  <a href="ml.html#svr_trainer">regression</a>  </li>
                   <li>Reduced-rank methods for large-scale <a href="ml.html#svm_c_ekm_trainer">classification</a>
                      and <a href="ml.html#krr_trainer">regression</a></li>
                   <li>Relevance vector machines for <a href="ml.html#rvm_trainer">classification</a> 
                       and <a href="ml.html#rvm_regression_trainer">regression</a> </li>
+                  <li>General purpose <a href="ml.html#one_vs_one_trainer">multiclass classification</a> tools</li>
                   <li>An online <a href="ml.html#krls">kernel RLS regression</a> algorithm</li>
                   <li>An online <a href="ml.html#svm_pegasos">SVM classification</a> algorithm</li>
-                  <li>An online kernelized <a href="ml.html#kcentroid">centroid estimator</a>/novelty detector</li>
+                  <li>An online kernelized <a href="ml.html#kcentroid">centroid estimator</a>/novelty detector</li> and
+                     offline support vector <a href="ml.html#svm_one_class_trainer">one-class classification</a>
                   <li>A kernelized <a href="ml.html#kkmeans">k-means</a> clustering algorithm</li>
                   <li><a href="ml.html#rbf_network_trainer">Radial Basis Function Networks</a></li>
                   <li><a href="ml.html#mlp">Multi layer perceptrons</a> </li>  
diff --git a/docs/docs/release_notes.xml b/docs/docs/release_notes.xml
index e6ff2e651..10f4822d5 100644
--- a/docs/docs/release_notes.xml
+++ b/docs/docs/release_notes.xml
@@ -12,13 +12,61 @@
 
 <current>
 New Stuff:
+   - General Stuff 
+      - Added the promote template
+      - Added the basic_type template
+      - Added the assign_image_scaled() function
+      - Added the unordered_pair object.
+      - Added the symmetric_matrix_cache() function
+      - Added two new quadratic program solvers.  The solve_qp2_using_smo
+        and solve_qp3_using_smo objects.
 
+   - Machine Learning Stuff
+      - Added the svm_c_trainer object.  It implements C-SVM classification and
+        allows the user to set different C values for each class.
+      - Added the svm_one_class_trainer object. 
+      - Added the svr_trainer object.  It implements epsilon-insensitive
+        support vector regression.
+      - Added two new any objects.  The any_decision_function for containing 
+        decision function style objects and the any_trainer for trainers.
+      - Added cross_validate_regression_trainer()
+      - Added test_regression_function()
+      - Added the probabilistic() function.  It is a trainer adapter that
+        simply calls train_probabilistic_decision_function().
+      - Added tools for multiclass classification 
+         - Added one_vs_one_trainer
+         - Added one_vs_all_trainer
+         - Added cross_validate_multiclass_trainer()
+         - Added test_multiclass_decision_function()
+ 
 Non-Backwards Compatible Changes:
+  - invalid_svm_nu_error has been renamed to invalid_nu_error.
+  - Changed the pixel_traits so that signed grayscale pixel types are allowed.  
+    This involved adding a few new fields to pixel_traits.  I also changed the 
+    get_pixel_intensity() function so that its return value is of the same type 
+    as the basic pixel type rather than always being unsigned long.
+  - Removed the kernel_type typedef from the normalized function since this
+    meta-object should be capable of working with non-kernel decision functions.
+  - train_probabilistic_decision_function() no longer accepts column vectors of 
+    samples and labels.  Now it only accepts std::vectors of samples and labels.  
 
 Bug fixes:
+  - Fixed a bug in the deserialization code for the sparse kernels.  The bug
+    prevented code which used the deserialize() routine from compiling.
 
 Other:
-
+  - Changed the image display GUI widgets to use the assign_image_scaled() 
+    function internally.  Now they will accept just about any image and 
+    do the right thing.
+  - Modified the type_safe_union so that you can call apply_to_contents() on const
+    type_safe_unions.
+  - Added serialization support for std::pair objects.
+  - Made the train_probabilistic_decision_function() more general by making it work 
+    with any kind of trainer object rather than only ones which produce 
+    dlib::decision_function objects.  I also made it work with trainers that only 
+    take std::vectors.
+  - Added overloads to the config_reader's methods to allow it to load directly 
+    from a file name given as a string in addition to taking istream objects.
 </current>
 
 <!-- *******************************************************************************  -->