All entries.
Showing Items 511-520 of 537 on page 52 of 54: First Previous 47 48 49 50 51 52 53 54 Next

Logo Torch 5 5.1

by andresy - October 1, 2008, 04:25:12 CET [ Project Homepage BibTeX Download ] 10595 views, 1517 downloads, 2 subscriptions

Rating Whole StarWhole StarWhole StarWhole StarEmpty Star
(based on 1 vote)

About: 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 a easy and fast scripting [...]

Changes:

Initial Announcement on mloss.org.


Logo treelearn 1

by iskander - September 21, 2011, 16:12:27 CET [ Project Homepage BibTeX Download ] 2172 views, 507 downloads, 1 subscription

About: A python implementation of Breiman's Random Forests.

Changes:

Initial Announcement on mloss.org.


Logo TurboParser 2.0

by afm - October 11, 2012, 02:59:04 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 3864 views, 854 downloads, 1 subscription

About: TurboParser is a free multilingual dependency parser based on linear programming developed by André Martins. It is based on joint work with Noah Smith, Mário Figueiredo, Eric Xing, Pedro Aguiar.

Changes:

This version introduces a number of new features:

  • The parser does not depend anymore on CPLEX (or any other non-free LP solver). Instead, the decoder is now based on AD3, our free library for approximate MAP inference.

  • The parser now outputs dependency labels along with the backbone structure.

  • As a bonus, we now provide a trainable part-of-speech tagger, called TurboTagger, which can be used in standalone mode, or to provide part-of-speech tags as input for the parser. TurboTagger has state-of-the-art accuracy for English (97.3% on section 23 of the Penn Treebank) and is fast (~40,000 tokens per second).

  • The parser is much faster than in previous versions. You may choose among a basic arc-factored parser (~4,300 tokens per second), a standard second-order model with consecutive sibling and grandparent features (the default; ~1,200 tokens per second), and a full model with head bigram and arbitrary sibling features (~900 tokens per second).

Note: The runtimes above are approximate, and based on experiments with a desktop machine with a Intel Core i7 CPU 3.4 GHz and 8GB RAM. To run this software, you need a standard C++ compiler. This software has the following external dependencies: AD3, a library for approximate MAP inference; Eigen, a template library for linear algebra; google-glog, a library for logging; gflags, a library for commandline flag processing. All these libraries are free software and are provided as tarballs in this package.

This software has been tested on Linux, but it should run in other platforms with minor adaptations.


Logo Tuwo 1.0

by nowozin - May 19, 2009, 09:19:41 CET [ Project Homepage BibTeX Download ] 3662 views, 884 downloads, 1 subscription

About: C++ Library for High-level Computer Vision Tasks

Changes:

Initial Announcement on mloss.org.


Logo Two dimensional relaxed representation 1.0

by openpr_nlpr - November 4, 2013, 05:48:12 CET [ Project Homepage BibTeX Download ] 712 views, 146 downloads, 1 subscription

About: Q. Dong, Two-dimensional relaxed representation, Neurocomputing, 121:248-253, 2013, http://dx.doi.org/10.1016/j.neucom.2013.04.044

Changes:

Initial Announcement on mloss.org.


Logo Two stage Sparse Representation 1.0.0

by openpr_nlpr - December 2, 2011, 05:32:31 CET [ Project Homepage BibTeX Download ] 1119 views, 384 downloads, 1 subscription

About: This program implements a novel robust sparse representation method, called the two-stage sparse representation (TSR), for robust recognition on a large-scale database. Based on the divide and conquer strategy, TSR divides the procedure of robust recognition into outlier detection stage and recognition stage. The extensive numerical experiments on several public databases demonstrate that the proposed TSR approach generally obtains better classification accuracy than the state-of-the-art Sparse Representation Classification (SRC). At the same time, by using the TSR, a significant reduction of computational cost is reached by over fifty times in comparison with the SRC, which enables the TSR to be deployed more suitably for large-scale dataset.

Changes:

Initial Announcement on mloss.org.


Logo Uncorrelated Multilinear Discriminant Analysis 1.0

by hplu - July 7, 2012, 06:27:56 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 2555 views, 486 downloads, 1 subscription

About: A Matlab implementation of Uncorrelated Multilinear Discriminant Analysis (UMLDA) for dimensionality reduction of tensor data via tensor-to-vector projection

Changes:

Initial Announcement on mloss.org.


Logo Uncorrelated Multilinear Principal Component Analysis 1.0

by hplu - June 18, 2012, 17:23:52 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 2161 views, 433 downloads, 1 subscription

About: A Matlab implementation of Uncorrelated Multilinear PCA (UMPCA) for dimensionality reduction of tensor data via tensor-to-vector projection

Changes:

Initial Announcement on mloss.org.


Logo Universal Java Matrix Package 0.2.5

by arndt - February 9, 2010, 15:55:23 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 9918 views, 1779 downloads, 1 subscription

About: The Universal Java Matrix Package (UJMP) is a data processing tool for Java. Unlike JAMA and Colt, it supports multi-threading and is therefore much faster on current hardware. It does not only support matrices with double values, but instead handles every type of data as a matrix through a common interface, e.g. CSV files, Excel files, images, WAVE audio files, tables in SQL data bases, and much more.

Changes:

Meta data updated.


Logo UniverSVM 1.22

by fabee - October 16, 2012, 11:24:12 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 15918 views, 2500 downloads, 0 subscriptions

About: The UniverSVM is a SVM implementation written in C/C++. Its functionality comprises large scale transduction via CCCP optimization, sparse solutions via CCCP optimization and data-dependent [...]

Changes:

Minor changes: fix bug on set_alphas_b0 function (thanks to Ferdinand Kaiser - ferdinand.kaiser@tut.fi)


Showing Items 511-520 of 537 on page 52 of 54: First Previous 47 48 49 50 51 52 53 54 Next