MARLENA

MARLENA is novel technique able to explain the reasons behind any black-box multi-label classifier decision. It will generate an explanation in the form of a decision rule. You can find the details of this model in the related paper 'Explaining Multi-Label Black Box Classifiers for Health Applications'. This preliminary version of MARLENA works with tabular datasets

Tags
Data and Resources
To access the resources you must log in
  • Marlena codepython

    The resource: 'Marlena code' is not accessible as guest user. You must login to access it!
Additional Info
Field Value
Accessibility Both
AccessibilityMode Download
Area
Attribution requirements
Availability On-Line
Basic rights Download
CreationDate 2019-01-01
Creator Panigutti, Cecilia
Dependencies on Other SW
Distribution requirements
External Identifier
Field/Scope of use Any use
Hosting Environment
IP/Copyrights
Item URL http://data.d4science.org/ctlg/ResourceCatalogue/marlena
http://data.d4science.org/ctlg/ResourceCatalogue/marlena
License term /Not specified
Owner Panigutti, Cecilia
ProgrammingLanguage
RelatedPaper
Requirement of non-disclosure (confidentiality mark)
Restrictions on use
Semantic Coverage
Sublicense rights No
Territory of use World Wide
ThematicCluster Text and Social Media Mining
UsageMode Download
input
output
system:type SoBigData.eu: Method
Management Info
Field Value
Author Trasarti Roberto
Maintainer Trasarti Roberto
Version 1
Last Updated 27 January 2019, 00:04 (CET)
Created 27 January 2019, 00:01 (CET)