Projects running under linux.
Showing Items 1-20 of 282 on page 1 of 15: 1 2 3 4 5 6 Next Last

Logo Aboleth 0.7

by dsteinberg - December 14, 2017, 02:39:19 CET [ Project Homepage BibTeX Download ] 1693 views, 492 downloads, 3 subscriptions

About: A bare-bones TensorFlow framework for Bayesian deep learning and Gaussian process approximation

Changes:

Release 0.7.0

  • Update to TensorFlow r1.4.

  • Tutorials in the documentation on:

  • Interfacing with Keras

  • Saving/loading models

  • How to build a variety of regressors with Aboleth

  • New prediction module with some convenience functions, including freezing the weight samples during prediction.

  • Bayesian convolutional layers with accompanying demo.

  • Allow the number of samples drawn from a model to be varied by using placeholders.

  • Generalise the feature embedding layers to work on matrix inputs (instead of just column vectors).

  • Numerous numerical and usability fixes.


Logo sparkcrowd 0.1.5

by enriquegrodrigo - December 13, 2017, 13:13:35 CET [ Project Homepage BibTeX Download ] 729 views, 227 downloads, 3 subscriptions

About: A Spark package implementing algorithms for learning from crowdsourced big data.

Changes:

Changes: - Minor improvements in code and documentation


Logo Theano 1.0.1

by jaberg - December 7, 2017, 14:14:38 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 38321 views, 6467 downloads, 3 subscriptions

About: A Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Dynamically generates CPU and GPU modules for good performance. Deep Learning Tutorials illustrate deep learning with Theano.

Changes:

Theano 1.0.1 (6th of December, 2017)

This is a maintenance release of Theano, version 1.0.1, with no new features, but some important bug fixes.

Highlights (since 1.0.0):

  • Fixed compilation and improved float16 support for topK on GPU

  • NB: topK support on GPU is experimental and may not work for large input sizes on certain GPUs

  • Fixed cuDNN reductions when axes to reduce have size 1

  • Attempted to prevent re-initialization of the GPU in a child process

  • Fixed support for temporary paths with spaces in Theano initialization

  • Spell check pass on the documentation


Logo DFLsklearn, Hyperparameters optimization in Scikit Learn 0.1

by vlatorre - November 23, 2017, 13:14:36 CET [ Project Homepage BibTeX Download ] 424 views, 93 downloads, 1 subscription

About: A method to optimize the hyperparameters for machine learning methods implemented in Scikit-learn based on Derivative Free Optimization

Changes:

Initial Announcement on mloss.org.


Logo MLweb 1.1

by lauerfab - November 10, 2017, 11:34:48 CET [ Project Homepage BibTeX Download ] 12869 views, 3074 downloads, 3 subscriptions

About: MLweb is an open source project that aims at bringing machine learning capabilities into web pages and web applications, while maintaining all computations on the client side. It includes (i) a javascript library to enable scientific computing within web pages, (ii) a javascript library implementing machine learning algorithms for classification, regression, clustering and dimensionality reduction, (iii) a web application providing a matlab-like development environment.

Changes:
  • Add gaxpy() and documentation on in-place operations
  • Add loo() function to Classifier and Regression models
  • New contributed toolbox for RNN
  • Minor fixes

Logo Obandit 0.2

by fre - November 6, 2017, 14:33:02 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 756 views, 207 downloads, 2 subscriptions

About: Obandit is an Ocaml module for multi-armed bandits. It supports the EXP, UCB and Epsilon-greedy family of algorithms.

Changes:

Initial Announcement on mloss.org.


Logo AffectiveTweets 1.0.0

by felipebravom - November 1, 2017, 02:24:58 CET [ Project Homepage BibTeX Download ] 601 views, 194 downloads, 3 subscriptions

About: A WEKA package for analyzing emotion and sentiment of tweets.

Changes:

Initial Announcement on mloss.org.


Logo HIERDENC 1.0

by billandreo - October 31, 2017, 16:01:32 CET [ Project Homepage BibTeX Download ] 1192 views, 1210 downloads, 2 subscriptions

About: This is a tool for retrieving nearest neighbors and clustering of large categorical data sets represented in transactional form. The clustering is achieved via a locality-sensitive hashing of categorical datasets for speed and scalability.

Changes:

Initial Announcement on mloss.org.


Logo Accord.NET Framework 3.8.0

by cesarsouza - October 23, 2017, 20:50:27 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 42088 views, 7099 downloads, 2 subscriptions

About: The Accord.NET Framework is a .NET machine learning framework combined with audio and image processing libraries completely written in C#. It is a complete framework for building production-grade computer vision, computer audition, signal processing and statistics applications even for commercial use. A comprehensive set of sample applications provide a fast start to get up and running quickly, and an extensive online documentation helps fill in the details.

Changes:

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/tag/v3.8.0


Logo bufferkdtree 1.3

by fgieseke - October 20, 2017, 11:39:59 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 549 views, 96 downloads, 2 subscriptions

About: The bufferkdtree package is a Python library that aims at accelerating nearest neighbor computations using both k-d trees and modern many-core devices such as graphics processing units (GPUs).

Changes:

Initial Announcement on mloss.org.


Logo JMLR dlib ml 19.7

by davis685 - September 17, 2017, 15:10:23 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 206089 views, 31977 downloads, 5 subscriptions

About: This project is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

Changes:

This release upgrades dlib's CNN+MMOD object detector to support creating multi-class detectors. It also includes significant speed improvements, allowing the detector to run at 98fps when executed on a NVIDIA 1080ti GPU. This release also adds a new 5 point face landmarking model that is over 10x smaller than the 68 point model, runs faster, and works with both HOG and CNN generated face detections. It is now the recommended landmarking model to use for face alignment.


Logo JMLR Jstacs 2.3

by keili - September 13, 2017, 14:25:38 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 32557 views, 7481 downloads, 4 subscriptions

About: A Java framework for statistical analysis and classification of biological sequences

Changes:

New classes and packages:

  • Jstacs 2.3 is the first release to be accompanied by JstacsFX, a library for building JavaFX-based graphical user interfaces based on JstacsTools
  • new interface MultiThreadedFunction
  • new class LargeSequenceReader for reading large sequence files in chunks
  • new interface QuickScanningSequenceScore
  • new class RegExpValidator for checking String inputs against a regular expression
  • new class IUPACDNAAlphabet

New features and improvements:

  • Alignments may now handle different costs for insert and delete gaps
  • ListResults may now be constructed from Collections of ResultSets
  • Several minor improvements and bugfixes in many classes
  • Improvements of documentation of several classes

About: A non-iterative, incremental and hyperparameter-free learning method for one-layer feedforward neural networks without hidden layers. This method efficiently obtains the optimal parameters of the network, regardless of whether the data contains a greater number of samples than variables or vice versa. It does this by using a square loss function that measures errors before the output activation functions and scales them by the slope of these functions at each data point. The outcome is a system of linear equations that obtain the network's weights and that is further transformed using Singular Value Decomposition.

Changes:

Initial Announcement on mloss.org.


About: A non-iterative learning method for one-layer (no hidden layer) neural networks, where the weights can be calculated in a closed-form manner, thereby avoiding low convergence rate and also hyperparameter tuning. The proposed learning method, LANN-SVD in short, presents a good computational efficiency for large-scale data analytic.

Changes:

Initial Announcement on mloss.org.


About: An open-source framework for benchmarking of feature selection algorithms and cost functions.

Changes:

Initial Announcement on mloss.org.


Logo HyperStream 0.3.6

by tdiethe - July 27, 2017, 04:11:57 CET [ Project Homepage BibTeX Download ] 1347 views, 273 downloads, 1 subscription

About: Hyperstream is a large-scale, flexible and robust software package for processing streaming data.

Changes:

python 3 support; new API; bug fixes and enhancements


Logo Somoclu 1.7.4

by peterwittek - June 6, 2017, 15:48:11 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 33746 views, 6059 downloads, 3 subscriptions

About: Somoclu is a massively parallel implementation of self-organizing maps. It relies on OpenMP for multicore execution, MPI for distributing the workload, and it can be accelerated by CUDA on a GPU cluster. A sparse kernel is also included, which is useful for training maps on vector spaces generated in text mining processes. Apart from a command line interface, Python, Julia, R, and MATLAB are supported.

Changes:
  • New: Verbosity parameter in the command-line, Python, MATLAB, and Julia interfaces.
  • Changed: Calculation of U-matrix parallelized.
  • Changed: Moved feeding data to train method in the Python interface.
  • Fixed: The random seed was set to 0 for testing purposes. This is now changed to a wall-time based initialization.
  • Fixed: Sparse matrix reader made more robust.
  • Fixed: Compatibility with kohonen 3 resolved.
  • Fixed: Compatibility with Matplotlib 2 resolved.

Logo JMLR MSVMpack 1.5.1

by lauerfab - March 9, 2017, 12:29:37 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 31713 views, 9045 downloads, 2 subscriptions

About: MSVMpack is a Multi-class Support Vector Machine (M-SVM) package. It is dedicated to SVMs which can handle more than two classes without relying on decomposition methods and implements the four M-SVM models from the literature: Weston and Watkins M-SVM, Crammer and Singer M-SVM, Lee, Lin and Wahba M-SVM, and the M-SVM2 of Guermeur and Monfrini.

Changes:
  • Fix compilation error with recent gcc

Logo Armadillo library 7.800

by cu24gjf - March 8, 2017, 10:11:25 CET [ Project Homepage BibTeX Download ] 123760 views, 23720 downloads, 5 subscriptions

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

About: Armadillo is a high quality C++ linear algebra library, aiming towards a good balance between speed and ease of use. The function syntax is deliberately similar to MATLAB. Useful for algorithm development directly in C++, or quick conversion of research code into production environments (eg. software & hardware products).

Changes:
  • more accurate sparse eigen decomposition by eigs_sym() and eigs_gen()
  • more robust handling of non-square matrices by lu()
  • expanded qz() to optionally specify ordering of the Schur form
  • expanded .each_slice() in the Cube class to support matrix multiplication
  • expanded several functions to handle sparse matrices
  • added expmat_sym(), logmat_sympd(), sqrtmat_sympd() for handling symmetric matrices
  • added polyfit() and polyval() for polynomial fitting
  • fix for aliasing issue in convolution functions conv() and conv2()
  • fix for memory leak in the field class when compiling in C++11/C++14 mode

Logo OpenNN 3.1

by Sergiointelnics - March 3, 2017, 17:17:45 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 12303 views, 1895 downloads, 4 subscriptions

About: OpenNN is a software library written in C++ for advanced analytics. It implements neural networks, the most successful machine learning method. The library has been designed to learn from both data sets and mathematical models.

Changes:

New algorithms, correction of bugs.


Showing Items 1-20 of 282 on page 1 of 15: 1 2 3 4 5 6 Next Last