Revision history for Perl extension Algorithm::LibLinear

0.19    Mon Oct 15 2018
        - Bundle LIBLINEAR 2.21.
        - Add one more digit to numbers in scaling data file, to adapt to
          changes of svm-scale on LIBSVM 3.23 / LIBLINEAR 2.21.
          cf. https://github.com/cjlin1/libsvm/commit/e42465fde67fb10496ee269ff866ffd28ff71640

0.18    Wed Dec 27 2017
        - Bundle LIBLINEAR 2.20.

0.17    Thu Apr 13 2017
        - Bundle LIBLINEAR 2.11.

0.16    Tue Sep 30 2015
        - Bundle LIBLINEAR 2.1.

0.15    Fri Jul 10 2015
        - Bundle LIBLINEAR 2.01, which fixes memory leak and a bug.

0.14    Mon Jul 6 2015
        - Fix uninitialized struct bug.
        - Use Test::Deep for comparing floating point numbers.

0.13    Wed Jul 1 2015
        - Bundle LIBLINEAR 2.0.
        - Switch installer from Module::Install to Module::Build.
        - Algorithm::LibLinear: Add find_cost_parameter() method.

0.12    Sat Nov 1 2014
        - Fix test failures when using Test::Simple version 1.301001_062+.
          Thanks Chad Granum and Graham Knop.

0.11    Tue Oct 28 2014
        - Bundle LIBLINEAR 1.95.
        - Algorithm::LibLinear: Add "bias" optional costructor parameter.
        - Algorithm::LibLinaer::Model: Add bias() and coefficient() accessors.

0.10    Fri Mar 21 2014
        - Fix module dependency.
        - Minor documentation update.

0.09    Tue Jan 7 2014
        - Remove APIs deprecated in version 0.07.

0.08    Tue Nov 26 2013
        - Bundle LIBLINEAR 1.94, which fixes memory leak.

0.07    Thu Oct 1 2013
        - Introduce Algorithm::LibLinear::FeatureScaling class that replaces
          Algorithm::LibLinear::ScalingParameter. The ScalingParameter class
          and Algorithm::LibLinear::DataSet->scale() method are now deprecated
          and will be removed from the near future release.

0.06    Mon Jun 3 2013
        - Fix that predict() rounds result value even when the model is trained
          for regression.
        - predict_probability() now returns empty array when given model is not
          for logistic regression-based classification.

0.05    Sat Jun 1 2013
        - Fix incorrect behaviour of predict_values() due to my
          misunderstanding.
        - Relax type checking to not raise error on regression problem.

0.04    Sun May 19 2013
        - Fix incorrect sparse vector scaling.

0.03    Fri May 3 2013
        - Fix a test to pass on environment which is long double enabled.

0.02    Sat Mar 10 2013
        - Release for CPAN.

0.01    Tue Feb 26 2013
        - Original version