Martin Jullum
Martin Jullum
Home
Talks
Publications
Side projects
Light
Dark
Automatic
Explainable AI
Introduction to XAI
Basic general introduction to Explainable AI
Apr 5, 2024
BI Norwegian Business School, Nydalen, Oslo, Norway
Martin Jullum
Project
Slides
(NO) Hvordan forklarer vi kunstig intelligens?
Overordnet introduksjon til forskningsfeltet XAI og hvordan velge riktig forklaringsmetode
Jan 24, 2024
NAV - Arbeids- og velferdsdirektoratet, Fyrstikkalléen 1, Oslo
Martin Jullum
Project
Slides
Why AI needs maths and stats -- lessons from working in a CS field
Briefly about how we used our statistical mindset to incorporating feature dependence in Shapley values and Counterfactual Explanations
Dec 5, 2023
Blindern, UiO, Norway
Martin Jullum
Project
Slides
A ridiculously simple approach to counterfactual explanations
Brief introduction to our counterfactual explanation method MCCE
May 9, 2023
Online
Martin Jullum
Project
Slides
A ridiculously simple approach to counterfactual explanations
Introduction to our counterfactual explanation method MCCE
Mar 29, 2023
NTNU, Trondheim, Norway
Martin Jullum
Project
Slides
MCCE - Monte Carlo sampling of valid and realistic counterfactual explanations
Introduction to our counterfactual explanation method MCCE
Mar 9, 2023
Norweigan Computing Center, Oslo, Norway
Martin Jullum
Project
Slides
XAI Tree
Brief introduction and demo of our interactive tool for choosing XAI method
Nov 21, 2022
NAV, Oslo
Martin Jullum
Code
Project
Slides
Global model agnostic* explanation methods
Brief introduction and comparison of four global explanation methods
Apr 8, 2022
Online
Martin Jullum
Project
Slides
Shapley values for prediction explanation
Overview of the use of Shapley values for prediction explanation
Feb 3, 2022
Online
Martin Jullum
Project
Slides
Efficient and simple prediction explanations with groupShapley -- A practical perspective
Extending feature-wise Shapley value explanations to explanations through groups of features
Nov 30, 2021
Online
Martin Jullum
,
Annabelle Redelmeier
,
Kjersti Aas
Project
Slides
»
Cite
×