[Blends-commit] r2208 - projects/science/trunk/debian-science/tasks
Debian Pure Blends Subversion Commit
noreply at alioth.debian.org
Wed Jun 16 06:50:25 UTC 2010
Author: tille
Date: Wed Jun 16 06:50:18 2010
New Revision: 2208
URL: http://svn.debian.org/viewsvn/blends?rev=2208&view=rev
Log:
Added Pkg-Description fields to prospective packages (copied from ITP bugs)
Modified:
projects/science/trunk/debian-science/tasks/machine-learning
Modified: projects/science/trunk/debian-science/tasks/machine-learning
URL: http://svn.debian.org/viewsvn/blends/projects/science/trunk/debian-science/tasks/machine-learning?rev=2208&view=diff&r1=2208&r2=2207&p1=projects/science/trunk/debian-science/tasks/machine-learning&p2=projects/science/trunk/debian-science/tasks/machine-learning
==============================================================================
--- projects/science/trunk/debian-science/tasks/machine-learning (original)
+++ projects/science/trunk/debian-science/tasks/machine-learning Wed Jun 16 06:50:18 2010
@@ -68,30 +68,96 @@
Language: C/C++
WNPP: 585788
License: BSD
+Pkg-Description: Library for Large Linear Classification
+ LIBLINEAR is a linear classifier for data with millions of instances and
+ features. It supports
+ .
+ * L2-regularized classifiers
+ L2-loss linear SVM, L1-loss linear SVM, and logistic regression (LR)
+ * L1-regularized classifiers (after version 1.4)
+ L2-loss linear SVM and logistic regression (LR)
+ .
+ Main features of LIBLINEAR include
+ .
+ * Same data format as LIBSVM
+ * similar usage to LIBSVM
+ * Multi-class classification: 1) one-vs-the rest, 2) Crammer & Singer
+ * Cross validation for model selection
+ * Probability estimates (logistic regression only)
+ * Weights for unbalanced data
+ * MATLAB/Octave interface
Depends: libocas-dev
Homepage: http://cmp.felk.cvut.cz/~xfrancv/ocas/html/
Language: C
WNPP: 585789
License: GPL-3
+Pkg-Description: OCAS solver for training linear SVM classifiers
+ This library implements Optimized Cutting Plane Algorithm (OCAS) for training
+ linear SVM classifiers from large-scale data. The computational effort of OCAS
+ scales with O(m log m) where m is the sample size. In an extensive empirical
+ evaluation OCAS significantly outperforms current state of the art SVM solvers,
+ like SVM^light, SVM^perf and BMRM, achieving speedups of over 1,000 on some
+ datasets over SVM^light and 20 over SVM^perf, while obtaining the same precise
+ Support Vector solution.
+ .
+ * SVM solvers for training linear classifiers from large scale-data
+ * Binary (two-class) and genuine multi-class SVM formulations
+ * Optimized code written in C
+ * Reads examples from SVM^light format
+ * Optimized for both sparse and dense features
+ * Parallelized version of the binary solver
+ * binary solver)
+ * Tools for classification
+ * Training translation invariant image classifiers from virtual examples
+ * Functions for computing image features based on Local Binary Patterns
+ * (LBP)
Depends: python-pyevolve
Homepage: http://pyevolve.sourceforge.net
Language: Python
WNPP: 580924
License: PSF derivate
+Pkg-Description: Complete genetic algorithm framework written in pure python
+ Pyevolve was developed to be a complete genetic algorithm framework written in
+ pure python. The main objectives of Pyevolve are:
+ .
+ * written in pure python - to maximize the cross-platform aspect
+ * easy to use API - the API must be easy to the end-user
+ * see the evolution - the user can and must see and interact with the
+ evolution statistics, graphs, etc.
+ * extensible - the API must be extensible, the user can create
+ new representations, genetic operators such as
+ crossover, mutation, etc.
+ * fast - the design must be optimized for performance
+ * common features - the framework must implement the most common
+ features: selectors like roulette wheel,
+ tournament, ranking, uniform. Scaling schemes
+ such as linear scaling, etc.
+ * default parameters - we must have default operators, settings, etc
+ in all options
Depends: flann
Homepage: http://www.cs.ubc.ca/~mariusm/index.php/FLANN/FLANN
Language: C++
WNPP: 581903
License: BSD
+Pkg-Description: Fast Library for Approximate Nearest Neighbors
+ FLANN is a library for performing fast approximate nearest neighbor searches
+ in high dimensional spaces. It contains a collection of algorithms we found
+ to work best for nearest neighbor search and a system for automatically
+ choosing the best algorithm and optimum parameters depending on the dataset.
Depends: lua-torch5
Homepage: http://torch5.sourceforge.net
Language: C, Lua
WNPP: 490204
License: BSD
+Pkg-Description: A matlab-like environment for state-of-the-art machine learning algorithms.
+ Torch5 provides a Matlab-like environment for state-of-the-art machine
+ learning algorithms. It is easy to use and provides a very efficient
+ implementation, thanks to an easy and fast scripting language (Lua) and
+ a underlying C implementation.
Depends: lush
Why: LUSH is a generic Lisp environment for numeric computation, but
More information about the Blends-commit
mailing list