All entries.
Showing Items 31-40 of 604 on page 4 of 61: Previous 1 2 3 4 5 6 7 8 9 Next Last

Logo JMLR Darwin 1.9

by sgould - September 8, 2015, 06:50:37 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 41774 views, 8674 downloads, 4 subscriptions

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


Version 1.9:

  • Replaced drwnInPaint class with drwnImageInPainter class and added inPaint application
  • Added function to read CIFAR-10 and CIFAR-100 style datasets (see
  • Added drwnMaskedPatchMatch, drwnBasicPatchMatch, drwnSelfPatchMatch and basicPatchMatch application
  • drwnPatchMatchGraph now allows multiple matches to the same image
  • Upgraded wxWidgets to 3.0.2 (problems on Mac OS X)
  • Switched Mac OS X compilation to libc++ instead of libstdc++
  • Added Python scripts for running experiments and regression tests
  • Refactored drwnGrabCutInstance class to support both GMM and colour histogram model
  • Added cacheSortIndex to drwnDecisionTree for trading-off speed versus memory usage
  • Added mexLoadPatchMatchGraph for loading drwnPatchMatchGraph objects into Matlab
  • Improved documentation, other bug fixes and performance improvements

About: Nowadays, this is very popular to use the deep architectures in machine learning. Deep Belief Networks (DBNs) are deep architectures that use stack of Restricted Boltzmann Machines (RBM) to create a powerful generative model using training data. DBNs have many ability like feature extraction and classification that are used in many applications like image processing, speech processing and etc. According to the results of the experiments conducted on MNIST (image), ISOLET (speech), and 20 Newsgroups (text) datasets, it was shown that the toolbox can learn automatically a good representation of the input from unlabeled data with better discrimination between different classes. In addition, the toolbox supports different sampling methods (e.g. Gibbs, CD, PCD and our new FEPCD method), different sparsity methods (quadratic, rate distortion and our new normal method), different RBM types (generative and discriminative), GPU, etc. The toolbox is a user-friendly open source software and is freely available on the website.


New in toolbox

  • Bug was fixed for computeBatchSize function in Linux.
  • Revision of some demo scripts. cardinal

Logo r-cran-CORElearn 1.47.1

by r-cran-robot - September 3, 2015, 00:00:00 CET [ Project Homepage BibTeX Download ] 8741 views, 2082 downloads, 0 subscriptions

About: Classification, Regression and Feature Evaluation


Fetched by r-cran-robot on 2015-11-01 00:00:05.298141

Logo YCML 0.2.2

by yconst - August 24, 2015, 20:28:45 CET [ Project Homepage BibTeX Download ] 799 views, 149 downloads, 3 subscriptions

About: A Machine Learning framework for Objective-C and Swift (OS X / iOS)


Initial Announcement on

Logo Java Data Mining Package 0.3.0

by arndt - August 19, 2015, 15:44:46 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 1117 views, 207 downloads, 3 subscriptions

About: A Java library for machine learning and data analytics


Initial Announcement on

Logo jLDADMM 1.0

by dqnguyen - August 19, 2015, 12:52:36 CET [ Project Homepage BibTeX Download ] 752 views, 171 downloads, 2 subscriptions

About: The Java package jLDADMM is released to provide alternative choices for topic modeling on normal or short texts. It provides implementations of the Latent Dirichlet Allocation topic model and the one-topic-per-document Dirichlet Multinomial Mixture model (i.e. mixture of unigrams), using collapsed Gibbs sampling. In addition, jLDADMM supplies a document clustering evaluation to compare topic models.


Initial Announcement on

Logo Presage 0.9.1

by Dzmitry_Lahoda - August 18, 2015, 10:13:05 CET [ BibTeX Download ] 509 views, 153 downloads, 3 subscriptions

About: Presage is an intelligent predictive text entry platform.


Initial Announcement on

Logo Sparse Compositional Metric Learning v1.1

by bellet - August 16, 2015, 16:41:20 CET [ BibTeX BibTeX for corresponding Paper Download ] 2490 views, 891 downloads, 2 subscriptions

About: Scalable learning of global, multi-task and local metrics from data


Various minor bug fixes and improvements. The basis and triplet generation now fully supports with datasets with very small classes and arbitrary labels (no need to be consecutive or positive). The computational and memory efficiency of the code when data is high dimensional has been largely improved, and we generate a rectangular (smaller) projection matrix when the number of selected basis is smaller than the dimension. K-NN classification with local metrics has been optimized and made significantly less costly in both time and memory.

Logo OpenNN 2.2

by Sergiointelnics - August 10, 2015, 16:56:57 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 3866 views, 689 downloads, 3 subscriptions

About: OpenNN is an open source class library written in C++ programming language which implements neural networks, a main area of deep learning research. The library has been designed to learn from both data sets and mathematical models.


New algorithms, correction of bugs.

Logo libnabo 1.0.6

by smagnenat - August 5, 2015, 12:16:40 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 10070 views, 2260 downloads, 3 subscriptions

About: libnabo is a fast K Nearset Neighbor library for low-dimensional spaces.

  • Reset point indices of results with distances exceeding threshold (#23, #24)
  • Fine tune the find_package() capability and add uninstall target (#22)
  • Fixed compiler warning (#18)
  • Added OpenMP support (#20, #21)
  • Build type tuning (#19)
  • Fix: terminal comma in enum requires C++11
  • Fix UBSAN error calculating maxNodeCount (#16, #17)
  • Fixed tiny (yet significant) error in the Python doc strings (#15)
  • Compile static lib with PIC (#14)
  • Added configure scripts for full catkinization
  • Catkinization of libnabo (following REP136)
  • Update Added Simon as the maintainer.
  • [test] use CLOCK_PROF for NetBSD build
  • Fixed CppCheck warning. Fix broken install when doxygen is not found
  • Fix cmake stylistic issue
  • Make python install respect custom CMAKE_INSTALL_PREFIX
  • Fix broken install when doxygen is not found

Showing Items 31-40 of 604 on page 4 of 61: Previous 1 2 3 4 5 6 7 8 9 Next Last