Unified and efficient Machine Learning
Shogun implements a wide range of unified and efficient machine learning algorithms. The library allows easy and seamless combination of multiple data representations, algorithm classes, and general-purpose tools. This enables both rapid prototyping of data pipelines and quick implementations of new algorithms. Shogun combines modern software architecture in C++ with an efficient low-level computing backend and cutting-edge algorithm implementations to solve large-scale machine learning problems. The automatically generated interfaces allow to use Shogun from many modern high-level languages under a unified API.
We value and focus on our community of developers and users, encouraging and catalyzing learning experiences in machine learning, scientific computing, software-engineering, and project organisation.
Starting in 1999, the project has come a long way in terms of code-base, developer team, and use-cases. The current project focus continues being not on adding new ML algorithms, but rather on improving the usability in particular
- modernization of the framework
- applications & user experiences
- algorithm efficiency & benchmarks