Shark & Machine Learning 3.1
Shark 3.1 Released
We are happy to announce the official release of Shark 3.1.0.
Shark 3.0 Released
We are happy to announce the official release of Shark 3.0.0.
Shark moves to GitHub
Shark moved to GitHub. Please update your repositories, see the downloads page for more details.
Shark goes LGPL
As of , Shark is distributed under the permissive
Gold Prize for Shark alpha-release
We are happy to announce that our alpha-release
of Shark 3.0 has won the Gold Prize at the
About Shark
Shark is a fast, modular, feature-rich open-source C++ machine learning library.
It provides methods for linear and nonlinear optimization, kernel-based learning
algorithms, neural networks, and various other machine learning techniques (see the
below). It serves as a powerful toolbox for real world applications as well as
research. Shark depends on Boost and CMake. It is compatible with Windows, Solaris,
MacOS&X, and Linux. Shark is licensed under the permissive
GNU Lesser General Public License.
The current stable version is Shark&3.1, released 1-3-2015.
Shark&3 is incompatible with earlier versions of Shark. It is a
nearly complete rewrite with cleaner interfaces, better code structure,
and also better performance. Shark&2 is not supported any longer.
Shark 3.1 includes minor interface changes compared to 3.0 Almost all programs should be compatible
Source Packages
We have two source packages available:
Shark Repository
Get the current Shark repository snapshot:
git clone /Shark-ML/Shark/
Linux and Mac OSlibrary and unit tests
Windowslibrary only, no unit tests
Where to start?
Why Shark?
Speed and flexibility
Shark provides an excellent trade-off between flexibility and
ease-of-use on the one hand, and computational efficiency on the other.
One for all
Shark offers numerous algorithms from various machine learning and computational intelligence domains in a way that they can be easily combined and extended.
Unique features
Shark comes with a lot of powerful algorithms that are to our best knowledge not implemented in any other library, for example in the domains of model selection and training of binary and multi-class SVMs, or evolutionary single- and multi-objective optimization.
Selected features
Shark currently supports:
Supervised learning
Linear discriminant analysis (LDA), Fisher-LDA
Linear regression
Support vector machines (SVMs) for one-class, binary and true multi-category classification a includes fast variants for linear kernels.
Feed-forward and recurrent multi-layer artificial neural networks
Radial basis function networks
Regularization networks as well as Gaussian processes for regression
Iterative nearest neighbor classification and regression
Decision trees and random forests
Unsupervised learning
Principal component analysis
Restricted Boltzmann machines (including many state-of-the-art learning algorithms)
Hierarchical clustering
Data structures for efficient distance-based clustering
Evolutionary algorithms
Single-objective optimization (e.g., CMA-ES)
Multi-objective optimization (in particular, highly efficient algorithms for computing as well as approximating the contributing hypervolume)
Basic linear algebra and optimization algorithms
Credits and Copyright
Citing Shark
We kindly ask you to cite Shark in academic work as:
Christian Igel, Verena Heidrich-Meisner, and Tobias Glasmachers.
Journal of Machine Learning Research 9, pp. 993-996, 2008.
The article's bibtex entry reads:
@Article{shark08,
author = {Christian Igel and Verena Heidrich-Meisner and Tobias Glasmachers},
title = {Shark},
journal = {Journal of Machine Learning Research},
year = {2008},
volume = {9},
pages = {993--996}
The Shark library is made available under the
Hosting institutions
The Shark machine learning library is jointly maintained by researchers fromWhale Sharks - Whale Shark Pictures - Whale Shark Facts - National Geographic
Advertisement
Whale Shark
Rhincodon typus
As the largest fish in the sea, reaching lengths of 40 feet (12 meters) or more, whale sharks have an enormous menu from which to choose. Fortunately for most sea-dwellers—and us!—their favorite meal is plankton. They scoop these tiny plants and animals up, along with any small fish that happen to be around, with their colossal gaping mouths while swimming close to the water's surface.FeedingThe whale shark, like the world's second largest fish, the basking shark, is a filter feeder. In order to eat, the beast juts out its formidably sized jaws and passively filters everything in its path.
The mechanism is theorized to be a technique called “cross-flow filtration,” similar to some bony fish and baleen whales.The whale shark's flattened head sports a blunt snout above its mouth with short barbels protruding from its nostrils. Its back and sides are gray to brown with white spots among pale vertical and horizontal stripes, and its belly is white. Its two dorsal fins are set rearward on its body, which ends in a large dual-lobbed caudal fin (or tail).PopulationPreferring warm waters, whale sharks populate all tropical seas. They are known to migrate every spring to the continental shelf of the central west coast of Australia. The coral spawning of the area's Ningaloo Reef provides the whale shark with an abundant supply of plankton.Although massive, whale sharks are docile fish and sometimes allow swimmers to hitch a ride. They are currently listed as
however, they continue to be hunted in parts of Asia, such as the Philippines.
Fish Videos
More Sharks
Shark Features
Learn all you wanted to know about sharks with videos, quizzes, puzzles, and more.
Science and sport fishing join forces for a never-before-attempted research effort to study massive great white sharks in the wild.
Explore and discover the world's oceans like never before with facts, photos, news, video, and more!
Now under threat in the increasingly humanized seas, sharks still find refuge and freedom in the Bahamas. Join photographer Brian Skerry in what he describes as "a Garden of Eden for sharks."
On Nat Geo Wild
Animal News
PROMOTIONS
More From National GeographicAlso known as the Etmopterus benchleyi
If you are not a child, don’t have a child, or don’t know anyone with kids, there’s a chance you’ve never heard of a Hatchimal, the must-have toy for Christmas this year.
Allow me to introduce you: the Hatchimal is a plush little robot that comes...
Death wins Wikipedia pretty much every year. Since 2007, the page on everyone’s favorite online encyclopedia listing annual deaths has topped its yearly ranking of most-edited articles. (Pre-2007, that spot was taken by such non-controversial...
Christmas is coming soon, and if you’re a little behind on any gift shopping, December 22nd (today) is the last day that anything ordered with Amazon Prime’s free two-day shipping will be guaranteed to arrive by end of day on December 24th.
How about a nice game of Hide and Shriek or Fake News Charades?
Canada has recognized the obvious and declared high-speed broadband internet access a “basic telecommunications service” that every citizen should be able to access. Previously, only landline telephone services had received this designation from...
Do you remember the ‘90s? Of course you remember the ‘90s. We had Friends. Tamagotchi. Grunge. Pogs. Everyone ran around in flannel shirts, bleaching each others’ hair and singing Spice Girls. And because the ‘90s were so great (you were young,...Gymshark | Be a visionary. | Gym, fitness and sports clothing.
Featured Products
Featured Products
Free Express Delivery Over $75* (USD)
Free Express Delivery Over $75* (USD)
Live life in full colour.
Be the first to hear
Sign up to be the first to hear about our latest news, offers and events.
& 2016 Gymshark | All Rights Reserved.
Change Country
Your cart is empty.
total $0.00 USD