Project details for Accord.NET Framework

Screenshot Accord.NET Framework 2.1.5

by cesarsouza - February 21, 2011, 14:49:49 CET [ Project Homepage BibTeX Download ]

view (10 today), download ( 0 today ), 2 subscriptions

Description:

Accord.NET Framework is a C# framework which extends the excellent AForge.NET Framework with new tools and libraries.

The framework is comprised by libraries and sample applications demonstrating their features. Some of the libraries include:

  • Accord.Math - General math and matrix library with numerical decompositions and related linear algebra methods, such as Nonnegative Matrix Factorization, generalized Eigenvalue and others;
  • Accord.Statistics - library with statistical analysis and related tools, such as (Kernel) component and discriminant analysis, partial least squares and hidden Markov models;
  • Accord.Imaging - extension to the AForge.NET Imaging library with new filters and routines;
  • Accord.Neuro - extension to the AForge.NET Neuro library with new algorithms such as Levenberg-Marquardt with Bayesian regularization and Nguyen-Widrow weight initialization;
  • Accord.MachineLearning - extension to AForge's machine learning library with SVMs, K-Means and GMM clustering and related techniques;
  • Accord.Vision - extension to the AForge.NET Vision library with realtime object detectors and trackers such as Viola-Jones and Camshift;
  • Accord.Audio - experimental library with filters and audio processing routines.

For a complete listing of framework features, please see the feature list at http://accord-net.origo.ethz.ch/wiki/features

Changes to previous version:

The various works on this release have introduced some breaking interface changes, mainly in the Audio and Statistics namespaces.

  • Adding support for Independent Component Analysis;
  • Adding observation prediction in hidden Markov models;
  • Major reorganization of the hidden Markov models namespace;
  • Major architectural changes on the Accord.Audio namespace;
  • Adding a new algorithm for LDLt Cholesky matrix decomposition;
  • Adding Sparse versions of Gaussian, Polynomial, Laplacian, Sigmoid and Cauchy kernels.

And several other bugfixes and enhancements. For a complete list of changes, please see the full release notes at http://accord-net.origo.ethz.ch/download/2822

BibTeX Entry: Download
URL: Project Homepage
Supported Operating Systems: Linux, Windows
Data Formats: Agnostic
Tags: Svm, Kernel Methods, Algorithms, Classifiers, Statistics, Clustering Algorithm, Probability Estimation, Discriminant Analysis, Wavelet Transform, Principal Component Analysis, Algebra, Fourier Transfo
Archive: download here

Other available revisons

Version Changelog Date
2.10.0

This release aimed to provide improvements to the documentation. Most of the Univariate Distributions now include proper examples for all main functions and measures in their summary page. Also, a wide set of imaging methods, such as Haralick's set of textural features, the Local Binary Pattern, Gabor, Kirsch, and Variance filters have been added. Also includes the Denavit-Hartenberg model for kinematic chains and many updates, optimizations, corrections and bug-fixes in all major namespaces.

For a complete list of changes, please see the full release notes at the release details page at:

https://github.com/accord-net/framework/releases

September 9, 2013, 16:12:01
2.8.0

This release brings Cox's proportional hazards models and the partial Newton-Raphson learning algorithm. It also provides a reorganization of the (Hidden Conditional Random) Fields namespace, together with more bugfixes, improvements and optimizations.

For a complete list of changes, please see the full release notes at the release details page.

November 6, 2012, 07:01:01
2.7.1

This release fixes few bugs, adds new clustering algorithms, and provides a compatibility package to work with .NET 3.5.

For a complete list of changes, please see the full release notes at https://code.google.com/p/accord/source/browse/trunk/Release%20notes.txt

September 13, 2012, 01:57:18
2.6.0

This release adds support for RProp learning in HCRFs, optimizations to SVM learning and evaluation, a constrained QP solver based on the dual method of Goldfrab and Idnani, robust estimation of fundamental matrices and several other bugfixes and enhancements.

For a complete list of changes, please see the full release notes at http://accord-net.origo.ethz.ch/download/3982

April 4, 2012, 16:36:42
2.1.5

The various works on this release have introduced some breaking interface changes, mainly in the Audio and Statistics namespaces.

  • Adding support for Independent Component Analysis;
  • Adding observation prediction in hidden Markov models;
  • Major reorganization of the hidden Markov models namespace;
  • Major architectural changes on the Accord.Audio namespace;
  • Adding a new algorithm for LDLt Cholesky matrix decomposition;
  • Adding Sparse versions of Gaussian, Polynomial, Laplacian, Sigmoid and Cauchy kernels.

And several other bugfixes and enhancements. For a complete list of changes, please see the full release notes at http://accord-net.origo.ethz.ch/download/2822

February 21, 2011, 14:49:49
2.1.4
  • Adding support for more Haar cascade classifier definitions;
  • Optimizing Levenberg-Marquardt learning algorithm;

And several other bugfixes and enhancements. For a complete list of changes, please see the full release notes at http://accord-net.origo.ethz.ch/download/2312

December 3, 2010, 22:17:04
2.1.3
  • Adding Non-Negative Matrix Factorization, Continuous density Hidden Markov Models and Gaussian Mixture Models;
  • Heavy work on documentation.
November 3, 2010, 14:35:27
2.1.2

Initial Announcement on mloss.org.

October 16, 2010, 15:33:39

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.