About: BACKGROUND:Over the last decade several prediction methods have been developed for determining the structural and functional properties of individual protein residues using sequence and sequencederived information. Most of these methods are based on support vector machines as they provide accurate and generalizable prediction models. RESULTS:We present a general purpose protein residue annotation toolkit (svmPRAT) to allow biologists to formulate residuewise prediction problems. svmPRAT formulates the annotation problem as a classification or regression problem using support vector machines. One of the key features of svmPRAT is its ease of use in incorporating any userprovided information in the form of feature matrices. For every residue svmPRAT captures local information around the reside to create fixed length feature vectors. svmPRAT implements accurate and fast kernel functions, and also introduces a flexible windowbased encoding scheme that accurately captures signals and pattern for training eective predictive models. CONCLUSIONS:In this work we evaluate svmPRAT on several classification and regression problems including disorder prediction, residuewise contact order estimation, DNAbinding site prediction, and local structure alphabet prediction. svmPRAT has also been used for the development of stateoftheart transmembrane helix prediction method called TOPTMH, and secondary structure prediction method called YASSPP. This toolkit developed provides practitioners an efficient and easytouse tool for a wide variety of annotation problems. Availability: http://www.cs.gmu.edu/~mlbio/svmprat/ Changes:Initial Announcement on mloss.org.

About: Elefant is an open source software platform for the Machine Learning community licensed under the Mozilla Public License (MPL) and developed using Python, C, and C++. We aim to make it the platform [...] Changes:This release contains the Stream module as a first step in the direction of providing C++ library support. Stream aims to be a software framework for the implementation of large scale online learning algorithms. Large scale, in this context, should be understood as something that does not fit in the memory of a standard desktop computer. Added Bundle Methods for Regularized Risk Minimization (BMRM) allowing to choose from a list of loss functions and solvers (linear and quadratic). Added the following loss classes: BinaryClassificationLoss, HingeLoss, SquaredHingeLoss, ExponentialLoss, LogisticLoss, NoveltyLoss, LeastMeanSquareLoss, LeastAbsoluteDeviationLoss, QuantileRegressionLoss, EpsilonInsensitiveLoss, HuberRobustLoss, PoissonRegressionLoss, MultiClassLoss, WinnerTakesAllMultiClassLoss, ScaledSoftMarginMultiClassLoss, SoftmaxMultiClassLoss, MultivariateRegressionLoss Graphical User Interface provides now extensive documentation for each component explaining state variables and port descriptions. Changed saving and loading of experiments to XML (thereby avoiding storage of large input data structures). Unified automatic input checking via new static typing extending Python properties. Full support for recursive composition of larger components containing arbitrary statically typed state variables.

About: RLGlue allows agents, environments, and experiments written in Java, C/C++, Matlab, Python, and Lisp to inter operate, accelerating research by promoting software reuse in the community. Changes:RLGlue paper has been published in JMLR.

About: Reference implementation of the LASVM online and active SVM algorithms as described in the JMLR paper. The interesting bit is a small C library that implements the LASVM process and reprocess [...] Changes:Minor bug fix

About: This software implements the DeltaLDA model, which is a modification of the Latent Dirichlet Allocation (LDA) model. DeltaLDA can use multiple topic mixing weight priors to jointly model multiple [...] Changes:fixed some npy_intp[] memory leaks fixed phi normalization bug

About: The Computational Infrastructure for Operations Research (COINOR) project is an initiative to spur the development of opensource software for the operations research community. Changes:Initial Announcement on mloss.org.

About: SeDuMi is a software package to solve optimization problems over symmetric cones. This includes linear, quadratic, second order conic and semidefinite optimization, and any combination of these. Changes:Initial Announcement on mloss.org.

About: A desktop planetarium and sky map program which shows the sky from anywhere on Earth at any time. Changes:Removed erroneous topocentric code. Increased maximum zoom for detail on planets.

About: CMixSim is an open source package written in C for simulating finite mixture models with Gaussian components. With a vast number of clustering algorithms, evaluating performance is important. CMixSim provides an easy and convenient way of generating datasets from Gaussian mixture models with different levels of clustering complexity. CMixSim is released under the GNU GPL license. Changes:Initial Announcement on mloss.org.

About: CRFSuite is a speedoriented implementation of Conditional Random Fields (CRFs). This software features: parameter estimation using SGD and LBFGS, l1/l2 regularization, simple data I/O format, etc. Changes:Initial Announcement on mloss.org.

About: The goal of this project is to provide code for reading and writing machine learning data sets for as many programming languages as possible. Changes:Forgot to include the Java sources.

About: Pebl is a python library and command line application for learning the structure of a Bayesian network given prior knowledge and observations. Changes:Updated version to 1.0.1

About: Very fast implementation of the chisquared distance between histograms (or vectors with nonnegative entries). Changes:Removed bug in symmetric chisquare distance and updated python wrapper to python 2.5 compatiblity. 
About: SVQP1 and SVQP2 are QP solvers for training SVM. Changes:Initial Announcement on mloss.org.

About: A library for fast computation of Gauss transforms in multiple dimensions, using the Improved Fast Gauss Transform and a tree data structure. This library is useful for efficient Kernel Density [...] Changes:Initial Announcement on mloss.org.

About: A Kmeans clustering implementation for commandline, Python, Matlab and C. This algorithm yields the very same solution as standard Kmeans, even after each iteration. However it uses some triangle [...] Changes:Initial Announcement on mloss.org.

About: Disco is an opensource implementation of the [MapReduce framework](http://en.wikipedia.org/wiki/MapReduce) for distributed computing. As the original framework, Disco supports parallel [...] Changes:Initial Announcement on mloss.org.

About: Torch5 provides a matlablike environment for stateoftheart machine learning algorithms. It is easy to use and provides a very efficient implementation, thanks to a easy and fast scripting [...] Changes:Initial Announcement on mloss.org.

About: GMRFLib is a library in C for fast and exact simulation of Gaussian Markov Random Fields (GMRF) on graphs.unconditional simulation of a GMRF, conditional simulation from a GMRF Changes:Initial Announcement on mloss.org.
