All entries.
Showing Items 41-50 of 534 on page 5 of 54: Previous 1 2 3 4 5 6 7 8 9 10 Next Last

Logo Caffe 0.999

by sergeyk - May 20, 2014, 23:51:09 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 2316 views, 372 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:

https://github.com/BVLC/caffe/releases/tag/v0.999


Logo XGBoost v0.2

by crowwork - May 17, 2014, 07:27:59 CET [ Project Homepage BibTeX Download ] 1393 views, 220 downloads, 1 subscription

About: eXtreme gradient boosting (tree) library. Features: - Sparse feature format allows easy handling of missing values, and improve computation efficiency. - Efficient parallel implementation that optimizes memory and computation. - Python interface

Changes:

New features: - Python interface - New objectives: weighted training, pairwise rank, multiclass softmax - Comes with example script on Kaggle Higgs competition, 20 times faster than skilearn's GBRT


Logo Java deep neural networks with GPU 0.2.0-alpha

by hok - May 10, 2014, 14:22:30 CET [ Project Homepage BibTeX Download ] 670 views, 133 downloads, 2 subscriptions

About: GPU-accelerated java deep neural networks

Changes:

Initial Announcement on mloss.org.


Logo peewit 0.10

by lorenz - May 7, 2014, 16:04:18 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 14975 views, 2970 downloads, 1 subscription

About: peewit provides services for programming, running and result examination of machine learning experiments. It does not include any ML algorithms, has no GUI, and presumes certain uniformity of the experimental layout. But it does not make assumptions on the type of task under study. The current version-number is 0.10.

Changes:

v-cube with side-cubes


Logo Harry 0.2

by konrad - May 3, 2014, 18:48:38 CET [ Project Homepage BibTeX Download ] 1093 views, 236 downloads, 1 subscription

About: A Tool for Measuring String Similarity

Changes:

This release adds support for the Optimal Sequence Alignment distance (OSA) and fixes several minor bugs.


Logo Boosted Decision Trees and Lists 1.0.3

by melamed - May 1, 2014, 15:19:29 CET [ BibTeX Download ] 1910 views, 601 downloads, 2 subscriptions

About: Boosting algorithms for classification and regression, with many variations. Features include: Scalable and robust; Easily customizable loss functions; One-shot training for an entire regularization path; Continuous checkpointing; much more

Changes:
  • faster warm-start

  • made it easier to add more library paths to local makefile

  • added scripts to remove rare features and to standardize features


Logo PredictionIO 0.7.0

by simonc - April 29, 2014, 20:59:57 CET [ Project Homepage BibTeX Download ] 4778 views, 896 downloads, 2 subscriptions

About: Open Source Machine Learning Server

Changes:
  • Single machine version for small-to-medium scale deployments
  • Integrated GraphChi (disk-based large-scale graph computation) and algorithms: ALS, CCD++, SGD, CLiMF
  • Improved runtime for training and offline evaluation
  • Bug fixes

See release notes - https://predictionio.atlassian.net/secure/ReleaseNote.jspa?projectId=10000&version=11801


Logo RFD 1.0

by openpr_nlpr - April 28, 2014, 10:34:57 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 586 views, 106 downloads, 1 subscription

About: This is an unoptimized implementation of the RFD binary descriptor, which is published in the following paper. B. Fan, et al. Receptive Fields Selection for Binary Feature Description. IEEE Transaction on Image Processing, 2014. doi: http://dx.doi.org/10.1109/TIP.2014.2317981

Changes:

Initial Announcement on mloss.org.


About: RLLib is a lightweight C++ template library that implements incremental, standard, and gradient temporal-difference learning algorithms in Reinforcement Learning. It is an optimized library for robotic applications and embedded devices that operates under fast duty cycles (e.g., < 30 ms). RLLib has been tested and evaluated on RoboCup 3D soccer simulation agents, physical NAO V4 humanoid robots, and Tiva C series launchpad microcontrollers to predict, control, learn behaviors, and represent learnable knowledge. The implementation of the RLLib library is inspired by the RLPark API, which is a library of temporal-difference learning algorithms written in Java.

Changes:

Current release version is v2.0.


Logo WEKA 3.7.11

by mhall - April 24, 2014, 10:13:12 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 37596 views, 5372 downloads, 2 subscriptions

Rating Whole StarWhole StarWhole StarWhole StarEmpty Star
(based on 6 votes)

About: The Weka workbench contains a collection of visualization tools and algorithms for data analysis and predictive modelling, together with graphical user interfaces for easy access to this [...]

Changes:

In core weka:

  • Bagging and RandomForest are now faster if the base learner is a WeightedInstancesHandler
  • Speed-ups for REPTree and other classes that use entropy calculations
  • Many other code improvements and speed-ups
  • Additional statistics available in the output of LinearRegression and SimpleLinearRegression. Contributed by Chris Meyer
  • Reduced memory consumption in BayesNet
  • Improvements to the package manager: load status of individual packages can now be toggled to prevent a package from loading; "Available" button now displays the latest version of all available packages that are compatible with the base version of Weka
  • RandomizableFilteredClassifier
  • Canopy clusterer
  • ImageViewer KnowledgeFlow component
  • PMML export support for Logistic. Infrastructure and changes contributed by David Person
  • Extensive tool-tips now displayed in the Explorer's scheme selector tree lists
  • Join KnowledgeFlow component for performing an inner join on two incoming streams/data sets

In packages:

  • IWSSembeded package, contributed by Pablo Bermejo
  • CVAttributeEval package, contributed by Justin Liang
  • distributedWeka package for Hadoop
  • Improvements to multiLayerPerceptrons and addtion of MLPAutoencoder
  • Code clean-up in many packages

Showing Items 41-50 of 534 on page 5 of 54: Previous 1 2 3 4 5 6 7 8 9 10 Next Last