All entries.
Showing Items 201-210 of 624 on page 21 of 63: First Previous 16 17 18 19 20 21 22 23 24 25 26 Next Last

About: Nowadays this is very popular to use the deep architectures in machine learning. Deep Belief Networks (DBNs) are deep architectures that use a stack of Restricted Boltzmann Machines (RBM) to create a powerful generative model using training data. DBNs have many abilities such as feature extraction and classification that are used in many applications including image processing, speech processing, text categorization, etc. This paper introduces a new object oriented toolbox with the most important abilities needed for the implementation of DBNs. According to the results of the experiments conducted on the MNIST (image), ISOLET (speech), and the 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. Also on all the aforementioned datasets, the obtained classification errors are comparable to those of the state of the art classifiers. 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 based, etc. The toolbox is a user-friendly open source software in MATLAB and Octave and is freely available on the website.

Changes:

New in toolbox

  • Using GPU in Backpropagation
  • Revision of some demo scripts
  • Function approximation with multiple outputs
  • Feature extraction with GRBM in first layer

cardinal


Logo SCD 2.1

by ambujtewari - December 3, 2009, 22:21:45 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 9410 views, 1861 downloads, 1 subscription

About: A (randomized) coordinate descent procedure to minimize L1 regularized loss for classification and regression purposes.

Changes:

Fixed some I/O bugs. Lines that ended with whitespace were not read correctly in the previous version.


Logo Caffe 0.9999

by sergeyk - August 9, 2014, 01:57:58 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 11358 views, 1855 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


Logo r-cran-tree 1.0-29

by r-cran-robot - July 24, 2011, 00:00:00 CET [ Project Homepage BibTeX Download ] 9577 views, 1843 downloads, 1 subscription

About: Classification and regression trees

Changes:

Fetched by r-cran-robot on 2012-02-01 00:00:11.999664


Logo r-cran-gbm 2.0-8

by r-cran-robot - January 17, 2013, 00:00:00 CET [ Project Homepage BibTeX Download ] 8895 views, 1840 downloads, 1 subscription

About: Generalized Boosted Regression Models

Changes:

Fetched by r-cran-robot on 2013-04-01 00:00:05.019963


Logo K tree 0.4.2

by cdevries - July 4, 2011, 06:01:59 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 8711 views, 1839 downloads, 1 subscription

About: The K-tree is a scalable approach to clustering inspired by the B+-tree and k-means algorithms.

Changes:

Release of K-tree implementation in Python. This is targeted at a research and rapid prototyping audience.


Logo mcmkl 0.1

by ong - May 15, 2008, 15:30:44 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 9006 views, 1830 downloads, 1 subscription

About: We provide some preliminary code for multiclass multiple kernel learning in Matlab using CPLEX as a base solver.

Changes:

Initial Announcement on mloss.org.


Logo Nested Effects Models 2.4.0

by florian - July 8, 2008, 00:05:59 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 7125 views, 1828 downloads, 1 subscription

About: Nested Effects Models (NEMs) are a class of directed graphical models originally introduced to analyze the effects of gene perturbation screens with high-dimensional phenotypes. In contrast to other [...]

Changes:

Initial Announcement on mloss.org.


Logo CVXOPT 1.1

by jdahl - October 24, 2008, 21:37:16 CET [ Project Homepage BibTeX Download ] 6156 views, 1822 downloads, 0 comments, 2 subscriptions

Rating Whole StarWhole StarWhole StarWhole StarEmpty Star
(based on 3 votes)

About: CVXOPT is a free software package for convex optimization based on the Python programming language. It can be used with the interactive Python interpreter, on the command line by executing Python [...]

Changes:

Initial Announcement on mloss.org.


Logo Oger 1.1.3

by dvrstrae - August 13, 2012, 14:55:41 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 4724 views, 1818 downloads, 1 subscription

About: The OrGanic Environment for Reservoir computing (Oger) toolbox is a Python toolbox for rapidly building, training and evaluating modular learning architectures on large datasets.

Changes:

Initial Announcement on mloss.org.


Showing Items 201-210 of 624 on page 21 of 63: First Previous 16 17 18 19 20 21 22 23 24 25 26 Next Last