Shark is an open-source machine learning library. Shark privides 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.
15:05 Shark - by Christian Igel
16:15 Case - by Bjørn Bugge Grathwohl
16:45 A light meal
17:30 End of seminar
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.
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.
Shark is furthermore described in this paper, which has been accepted for Journal of Machine Learning Research.
Participation is free of charge.
Christian Igel, one of the architects of Shark, will present the framework at this seminar.