Personal tools
Home Rätsch Lab Meetings Machine Learning Tools Satellite Workshop
Navigation
 

Machine Learning Tools Satellite Workshop

A satellite workshop on machine learning tools, collocated with NIPS, held in Vancouver(B.C.) on December 4, 2005. This webpage is being continually updated.

Workshop Description

The aim of this meeting is to discuss the requirements and design of an open source machine learning toolbox. Recently, there has been a collaborative effort among NICTA Canberra, MPI Tuebingen, Fraunhofer Berlin, Fraunhofer Darmstadt, and INSA de Rouen to develop such a toolkit codenamed LINEAL. This set of tools uses Python as an interface language and currently uses PETSc as a numerical back end. The workshop is for the collaborators to investigate the different strategies for developing the toolbox.

We would appreciate an email to the contact persons below if you are interested in attending the meeting.

Organizers

Location

The workshop will be held on 4 December 2005 (one day before NIPS), between 9:00 am to 6:00 pm at the Hyatt Regency Vancouver, 655 Burrard Street, Vancouver BC, Canada.

Planned format:

The workshop will be a mixture of invited talks and open discussions. Everybody is welcome to attend but the speakers are by invitation only.

Morning session:

  • 9.00-10.00 Talks presenting open source libraries and languages (3 speakers, 20 minutes each)
  • 10.00-10.30 Coffee break
  • 10.30-12.00 Discussion about pros and cons of various open source languages and numerical tools.

Afternoon session:

  • 2.00-3.00 Talks presenting open source libraries and languages (3 speakers, 20 minutes each)
  • 3.00-3.30 Report of survey results on features that machine learners want from a toolbox, as well as previous and current efforts on coordinating the development of open source toolboxes.
  • 3.30-4.00 Coffee break
  • 4.00-6.00 Discussion among the LINEAL and ELEFANT collaborators.

Sponsors

This satellite workshop is sponsored by

Contact

For more information about the workshop contact S V N Vishwanathan or Cheng Soon Ong.

Document Actions