Shogun (toolbox)
| |
Shogun | |
---|---|
Type | Open Source |
Industry | Machine Learning |
Founded | 2006 |
Key people | Gunnar Rätsch (Founder), Soeren Sonnenburg (Founder), Sergey Lisitsyn, Heiko Strathmann, Fernando Iglesias, Viktor Gal |
Related Certifications | Certificate in Machine Learning Industry Overview |
The Shogun Machine learning toolbox provides a wide range of unified and efficient Machine Learning methods that seamlessly allows to easily combine multiple data representations, algorithm classes, and general purpose tools. This enables both rapid prototyping of data pipelines and extensibility in terms of new algorithms.
It offers features that span the whole space of Machine Learning methods, including many classical methods in classification, regression, dimensionality reduction, clustering, but also more advanced algorithm classes such as metric, multi-task, structured output, and online learning, as well as feature hashing, ensemble methods, and optimization. It also contains a number of exclusive algorithms such as a wealth of efficient SVM implementations, Multiple Kernel Learning, kernel hypothesis testing, Krylov methods, etc. [1]
History
- 1999 - Initiated by S. Sonnenburg and G. R¨atsch (SHOGUN)
- 2006 - First public release (June)
- 2008 - Used in 3rd party code (PyVMPA)
- 2013 - SHOGUN Release version 3.0.0. This release features 8 successful Google Summer of Code projects.
Features
SHOGUN is implemented in C++ and interfaces to Matlab(tm), R, Octave, Java, C#, Ruby, Lua and Python. Its features include :
- Modular, Extendible Object-Oriented Design
- Interfaces to Scripting Languages and Applications
- Efficient Native Feature Representations
- Eierlegendewollmilchsau Interface
- Modular Python SWIG based Interface
- Possible to stack together features of arbitrary types (sparse,dense, string) via CombinedFeatures and DotFeatures
- Chains of “preprocessors” (e.g. substracting the mean) can be attached to each feature object (on-the-fly pre-processing)
- Multiprocessor parallelization (training with up to 10 million examples and kernels)
- Implements COFFIN framework
Controversies
Top 5 Recent Tweets
Date | Author | Comment |
---|---|---|
August 24, 2018 | CppLibHunt | Awesome #C++ Weekly #114 is out https://t.co/jN2eupTqLW Featuring @stanimirovb @foonathan @fenbf @visualc @ShogunToolbox |