General

Location: ESAC, Madrid, Room B65
Date: May 14th & 15th, 2015

Participants

Agenda

Meeting will take place on Thursday 14th from 11:00 to 17:00 and Friday 15th from 10:00 to 13:00.


(1) WP Status
(2) Infrastructure discussion:

  • Data Source & conversion
  • Infrastructure (software & hardware) Define infrastructure: we have been making decisions (adopting Spark, for example) that have to be validated.
(3) DM features:
  • Data Mining Basic features
  • Advanced Data Mining Tools: Define list of advanced DM algorithms to be coded to complement MLLib for Spark.
(4) Implementation:
  • User Profile definition
  • Framework Execution Policies/Job scheduler: Define infrastructure access policies (batch, interactive, time allocation committees, general scheduling policies...)
  • User Interface
    • Decide on the feasibility of a client GUI for defining simple DM pipelines that creates a configuration file (XML?) and validates it before uploading and runnning.
    • Module for the creation of training sets from queries to the Gaia archive based on constraints to the Gaia (and possibly non-Gaia) data
    • DM models should be as much as possible re-usable. Where and how will we store them?
  • Visualization WP980 intergration
    • For visualisation and interactive analysis of DM results, we need the Visualisation software in WP980 to be able to access the DM results. Where and how will these be stored?
(5) Post-implementation
  • Grand Challenges
  • Workshops and schools
(6) Project coordination:
  • Assign coordinators of tasks and deadline
  • Draft SRS and SDD.
-- Cesc Julbe (erased user) - 2015-05-28

Comments

Topic revision: r1 - 2015-05-28 - CescJulbe
 
This site is powered by the TWiki collaboration platform Powered by PerlCopyright © 2008-2021 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback