All entries.
Showing Items 41-50 of 552 on page 5 of 56: Previous 1 2 3 4 5 6 7 8 9 10 Next Last

Logo Somoclu 1.4

by peterwittek - September 5, 2014, 13:01:14 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 5206 views, 987 downloads, 2 subscriptions

About: Somoclu is a massively parallel implementation of self-organizing maps. It relies on OpenMP for multicore execution, MPI for distributing the workload, and it can be accelerated by CUDA on a GPU cluster. A sparse kernel is also included, which is useful for training maps on vector spaces generated in text mining processes.

Changes:
  • Better Windows support.
  • Completed CUDA support for Python and R interfaces.
  • Faster compilation by removing unnecessary flags for nvcc
  • Support for CUDA 6.5.
  • Bug fixes: R version no longer needs separate code.

Logo JMLR Darwin 1.8

by sgould - September 3, 2014, 08:42:53 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 30860 views, 6463 downloads, 4 subscriptions

About: A platform-independent C++ framework for machine learning, graphical models, and computer vision research and development.

Changes:

Version 1.8:

  • Added Superpixel Graph Label Transfer (nnGraph) Project project
  • Added Python scripts for automating some projects
  • Added ability to pre-process features on-the-fly with one drwnFeatureTransform when applying or learning another drwnFeatureTransform
  • Fixed race condition in Windows threading (thanks to Edison Guo)
  • Switched Windows and Linux to build against OpenCV 2.4.9
  • Changed drwnMAPInference::inference to return upper and lower energy bounds
  • Added pruneRounds function to drwnBoostedClassifier
  • Added drwnSLICSuperpixels function
  • Added drwnIndexQueue class
  • mexLearnClassifier and mexAnalyseClassifier now support integer label types
  • Bug fix in mexSaveSuperpixels to support single channel

Logo XGBoost v0.3.0

by crowwork - September 2, 2014, 02:43:31 CET [ Project Homepage BibTeX Download ] 3333 views, 637 downloads, 2 subscriptions

About: xgboost: eXtreme Gradient Boosting It is an efficient and scalable implementation of gradient boosting framework. The package includes efficient linear model solver and tree learning algorithm. The package can automatically do parallel computation with OpenMP, and it can be more than 10 times faster than existing gradient boosting packages such as gbm or sklearn.GBM . It supports various objective functions, including regression, classification and ranking. The package is made to be extensible, so that user are also allowed to define there own objectives easily.

Changes:

New features: - R support that is now on CRAN

  • Faster tree construction module

  • Support for boosting from initial predictions

  • Linear booster is now parallelized, using parallel coordinated descent.


Logo r-cran-e1071 1.6-4

by r-cran-robot - September 1, 2014, 00:00:00 CET [ Project Homepage BibTeX Download ] 14656 views, 3082 downloads, 1 subscription

Rating Whole StarWhole StarWhole StarWhole Star1/2 Star
(based on 1 vote)

About: Misc Functions of the Department of Statistics (e1071), TU Wien

Changes:

Fetched by r-cran-robot on 2014-12-01 00:00:05.177526


Logo RLPy 1.3a

by bobklein2 - August 28, 2014, 14:34:35 CET [ Project Homepage BibTeX Download ] 2126 views, 475 downloads, 1 subscription

About: RLPy is a framework for performing reinforcement learning (RL) experiments in Python. RLPy provides a large library of agent and domain components, and a suite of tools to aid in experiments (parallelization, hyperparameter optimization, code profiling, and plotting).

Changes:
  • Fixed bug where results using same random seed were different with visualization turned on/off
  • Created RLPy package on pypi (Available at https://pypi.python.org/pypi/rlpy)
  • Switched from custom logger class to python default
  • Added unit tests
  • Code readability improvements (formatting, variable names/ordering)
  • Restructured TD Learning heirarchy
  • Updated tutorials

Logo Salad 0.5.0

by chwress - August 22, 2014, 17:54:56 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 4710 views, 849 downloads, 1 subscription

About: A Content Anomaly Detector based on n-Grams

Changes:

Lots and lots of cool new features and bugfixes ;)

  • Refinements to the user interface: This includes a progress indicator, colors, etc.
  • Determine the expected error (salad-inspect)
  • Enable the user to echo the used parametrization: salad [train|predict|inspect] --echo-params
  • Allow to set the input batch size as program argument: salad [train|predict|inspect] --batch-size
  • libsalad: The library allows to access salad's basic functions
  • Installers and precompiled binaries: Windows installer, Debian (ppa:chwress/salad) & RPM packages as well a generic linux installers.
  • Various minor bug fixes
  • Support for "length at end" zip files
  • Improve salad's usage in a 2-class setting: salad [train|predict|inspect] --input-filter

Logo r-cran-arules 1.1-5

by r-cran-robot - August 19, 2014, 00:00:00 CET [ Project Homepage BibTeX Download ] 16086 views, 3333 downloads, 3 subscriptions

About: Mining Association Rules and Frequent Itemsets

Changes:

Fetched by r-cran-robot on 2014-12-01 00:00:03.638241


Logo CURFIL 1.1

by hanschul - August 18, 2014, 13:54:31 CET [ Project Homepage BibTeX Download ] 672 views, 156 downloads, 1 subscription

About: CURFIL uses NVIDIA CUDA to accelerate random forest training and prediction for RGB and RGB-D images. It focuses on image labelling tasks, such as image segmentation or classification applications. CURFIL allows to search for optimal hyper-parameter configurations (e.g. using the hyperopt) package) by massively decreasing training time.

Changes:

Initial Announcement on mloss.org.


Logo Toeblitz Toolkit for Fast Toeplitz Matrix Operations 1.03

by cunningham - August 13, 2014, 02:21:36 CET [ BibTeX Download ] 2758 views, 696 downloads, 2 subscriptions

About: Toeblitz is a MATLAB/Octave package for operations on positive definite Toeplitz matrices. It can solve Toeplitz systems Tx = b in O(n*log(n)) time and O(n) memory, compute matrix inverses T^(-1) (with free log determinant) in O(n^2) time and memory, compute log determinants (without inverses) in O(n^2) time and O(n) memory, and compute traces of products A*T for any matrix A, in minimal O(n^2) time and memory.

Changes:

Adding a write-up in written/toeblitz.pdf describing the package.


Logo Caffe 0.9999

by sergeyk - August 9, 2014, 01:57:58 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 4565 views, 787 downloads, 2 subscriptions

About: Caffe aims to provide computer vision scientists with a clean, modifiable implementation of state-of-the-art 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 non-GPU 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


Showing Items 41-50 of 552 on page 5 of 56: Previous 1 2 3 4 5 6 7 8 9 10 Next Last