All entries.
Showing Items 101-110 of 628 on page 11 of 63: First Previous 6 7 8 9 10 11 12 13 14 15 16 Next Last

Logo Debellor 1.0

by mwojnars - July 30, 2009, 16:48:05 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 9946 views, 2545 downloads, 1 subscription

About: Debellor is a scalable and extensible platform which provides common architecture for data mining and machine learning algorithms of various types.

Changes:
  • Naming of numerous classes/methods/fields changed to be more accurate and comprehensible
  • Weka and Rseslib libraries updated to the newest versions: Weka 3.6.1 & Rseslib 3.0.1. Debellor's wrappers adapted
  • New class: CrossValidation - evaluator of trainable cells through cross-validation
  • New class: RMSE - calculation of Root Mean Squared Error score
  • Data objects can be compared and used in collections
  • ArffReader can read from a user-provided java.io.InputStream
  • More convenient use of parameters (setting values)
  • More convenient use of data objects and data types (construction, type casting)
  • Other minor improvements to existing classes
  • Javadoc extended

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 Deep Semantic Ranking Based Hashing 1.0

by openpr_nlpr - November 18, 2015, 07:25:16 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 1725 views, 318 downloads, 3 subscriptions

About: This algorithm is described in Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval. See https://github.com/zhaofang0627/cuda-convnet-for-hashing

Changes:

Initial Announcement on mloss.org.


Logo deepdetect 0.1

by beniz - June 2, 2015, 09:25:28 CET [ Project Homepage BibTeX Download ] 1907 views, 507 downloads, 3 subscriptions

About: A Deep Learning API and server

Changes:

Initial Announcement on mloss.org.


Logo DeltaLDA 0.1.1

by davidandrzej - July 16, 2009, 21:52:18 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 9811 views, 1740 downloads, 1 subscription

About: This software implements the DeltaLDA model, which is a modification of the Latent Dirichlet Allocation (LDA) model. DeltaLDA can use multiple topic mixing weight priors to jointly model multiple [...]

Changes:

-fixed some npy_intp[] memory leaks -fixed phi normalization bug


Logo Denoising TOF 3D images using confidence measures 1

by mafrank - August 17, 2011, 16:59:12 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 4871 views, 1004 downloads, 1 subscription

About: Denoising images via normalized convolution

Changes:

Initial Announcement on mloss.org.


Logo Dependency modeling toolbox 0.2

by lml - April 30, 2010, 14:38:45 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 10785 views, 1653 downloads, 1 subscription

About: Investigation of dependencies between multiple data sources allows the discovery of regularities and interactions that are not seen in individual data sets. The demand for such methods is increasing with the availability and size of co-occurring observations in computational biology, open data initiatives, and in other domains. We provide practical, open access implementations of general-purpose algorithms that help to realize the full potential of these information sources.

Changes:

Three independent modules (drCCA, pint, MultiWayCCA) have been added.


Logo DIANNE 0.5.0

by sbohez - October 25, 2016, 19:51:07 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 828 views, 102 downloads, 3 subscriptions

About: DIANNE is a modular software framework for designing, training and evaluating artificial neural networks on heterogeneous, distributed infrastructure . It is built on top of OSGi and AIOLOS and can transparently deploy and redeploy (parts of) a neural network on multiple machines, as well as scale up training on a compute cluster.

Changes:

Initial Announcement on mloss.org.


Logo Differential Dependency Network cabig cytoscape plugin 1.0

by cbil - October 27, 2013, 17:31:58 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 3314 views, 771 downloads, 1 subscription

About: DDN learns and visualize differential dependency networks from condition-specific data.

Changes:

Initial Announcement on mloss.org.


Logo DiffSharp 0.7.7

by gbaydin - January 4, 2016, 00:57:35 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 11552 views, 2273 downloads, 3 subscriptions

About: DiffSharp is a functional automatic differentiation (AD) library providing gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products as higher-order functions. It allows exact and efficient calculation of derivatives, with support for nesting.

Changes:

Fixed: Bug fix in forward AD implementation of Sigmoid and ReLU for D, DV, and DM (fixes #16, thank you @mrakgr)

Improvement: Performance improvement by removing several more Parallel.For and Array.Parallel.map operations, working better with OpenBLAS multithreading

Added: Operations involving incompatible dimensions of DV and DM will now throw exceptions for warning the user


Showing Items 101-110 of 628 on page 11 of 63: First Previous 6 7 8 9 10 11 12 13 14 15 16 Next Last