Shark: Machine Learning Framework til C++ – University of Copenhagen

Shark: Machine Learning Framework til C++

Christian Igel, one of the architects of Shark, will present the framework at this seminar

Shark is an open-source machine learning library. Shark provides very high performance in areas of Machine Learning for highly efficient implementations of mathematically sound algorithms, which are not all available in other libraries. Shark has been developing for almost 10 years and has therefore reached some maturity.

Sign up on the Alexandra Institute's website

Program

15:00   Welcome
15:05   Presentation of Shark by Professor Christian Igel, Dept. of Computer Science, Copenhagen University
16:15   The tool by postdoc Oswin Krause, Dept. of Computer Science, Copenhagen University
16:45   A light meal
17:30   End of seminar

Why Shark?

  • Speed and flexibility
    Shark provides an excellent trade-off between flexibility an 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.