The Alexandra Institute // Right Now // Events // 2018 // Shark: Machine Learning Framework for C++

Shark: Machine Learning Framework for C++

Event

27-02-2018

Shark: Machine Learning Framework for 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.

 

Agenda

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.

 

FACTS

More about Shark

Shark is furthermore described in this paper, which has been accepted for Journal of Machine Learning Research.

 

Date:
27-02-2018 15:00 to 17:30
Place:
Copenhagen University, Njalsgade 76, 2300 Copenhagen S
Price:
Participation is free of charge
Organisers:

The Alexandra Institute in cooperation with DIKU Business Club, Nordic.ai, InfinIT and Symbion

Machine Learning Specialist
+45 93 50 88 22
Njalsgade 76, 3. sal, 2300 København S
.