About: This project is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems. Changes:This release adds a number of new features, most important of which is a deep convolutional neural network version of the maxmargin object detection algorithm. This tool makes it very easy to create high quality object detectors. See http://dlib.net/dnn_mmod_ex.cpp.html for an introduction.

About: learn optimized scoring systems using MATLAB and the CPLEX Optimization Studio Changes:Initial Announcement on mloss.org.

About: Armadillo is a high quality C++ linear algebra library, aiming towards a good balance between speed and ease of use. The function syntax is deliberately similar to MATLAB. Useful for algorithm development directly in C++, or quick conversion of research code into production environments (eg. software & hardware products). Changes:

About: A Content Anomaly Detector based on nGrams Changes:A teeny tiny fix to correctly handle input strings shorter than a registers width

About: A Tool for Measuring String Similarity Changes:This release fixes the incorrect implementation of the bag distance.

About: A Python based library for running experiments with Deep Learning and Ensembles on GPUs. Changes:Initial Announcement on mloss.org.

About: A Java framework for statistical analysis and classification of biological sequences Changes:New classes and packages:
New features and improvements:

About: A Tool for Embedding Strings in Vector Spaces Changes:Support for explicit selection of granularity added. Several minor bug fixes. We have reached 1.0

About: Caffe aims to provide computer vision scientists with a clean, modifiable implementation of stateoftheart deep learning algorithms. We believe that Caffe is the fastest available GPU CNN implementation. Caffe also provides seamless switching between CPU and GPU, which allows one to train models with fast GPUs and then deploy them on nonGPU clusters. Even in CPU mode, computing predictions on an image takes only 20 ms (in batch mode). Changes:LOTS of stuff: https://github.com/BVLC/caffe/releases/tag/v0.9999

About: Boosting algorithms for classification and regression, with many variations. Features include: Scalable and robust; Easily customizable loss functions; Oneshot training for an entire regularization path; Continuous checkpointing; much more Changes:

About: Scriptfriendly commandline tools for machine learning and data mining tasks. (The commandline tools wrap functionality from a public domain C++ class library.) Changes:Added support for CUDA GPUparallelized neural network layers, and several other new features. Full list of changes at http://waffles.sourceforge.net/docs/changelog.html

About: Universal Pythonwritten numerical optimization toolbox. Problems: NLP, LP, QP, NSP, MILP, LSP, LLSP, MMP, GLP, SLE, MOP etc; general logical constraints, categorical variables, automatic differentiation, stochastic programming, interval analysis, many other goodies Changes:http://openopt.org/Changelog

About: GPUaccelerated java deep neural networks Changes:Initial Announcement on mloss.org.

About: HierLearning is a C++11 implementation of a generalpurpose, multiagent, hierarchical reinforcement learning system for sequential decision problems. Changes:Initial Announcement on mloss.org.

About: The CTBNRLE is a C++ package of executables and libraries for inference and learning algorithms for continuous time Bayesian networks (CTBNs). Changes:compilation problems fixed

About: GPgrid toolkit for fast GP analysis on grid input Changes:Initial Announcement on mloss.org.

About: A Matlab implementation of Multilinear PCA (MPCA) and MPCA+LDA for dimensionality reduction of tensor data with sample code on gait recognition Changes:

About: A fast and robust learning of Bayesian networks Changes:Initial Announcement on mloss.org.

About: SVDFeature is a toolkit for developing generic collaborative filtering algorithms by defining features. Changes:JMLR MLOSS version.

About: ReFr is a software architecture for specifying, training and using reranking models. Changes:Initial Announcement on mloss.org.
