User-Based Experiment Guidelines for Measuring Interpretability in Machine Learning

Adrien Bibal; Bruno Dumas; Benoît Frénay

User-Based Experiment Guidelines for Measuring Interpretability in Machine Learning

Adrien Bibal, Bruno Dumas, Benoît Frénay

Research output: Contribution in Book/Catalog/Report/Conference proceeding › Conference contribution

43 Downloads (Pure)

Abstract

With the advent of high-performance black-box models, interpretability is becoming a hot topic today in machine learning. While a lot of research is
done on interpretability, machine learning researchers do not have precise guidelines for setting up user-based experiments. This paper provides well-established guidelines from the human-computer interaction community.

Original language	English
Title of host publication	EGC Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence
Place of Publication	Metz, France
Publication status	Published - 2019

Keywords

Machine learning
Interpretability
Guidelines

Access to Document

2019-Bibal-User_Experiment_Guidelines_for_Measuring_Interpretability_in_Machine_LearningFinal published version, 67.5 KB

Interpretability and Explainability in Machine Learning and their Application to Nonlinear Dimensionality Reduction
Bibal, A. (Author)FRENAY, B. (Supervisor), VANHOOF, W. (President), Cleve, A. (Jury), Dumas, B. (Jury), Lee, J. A. (Jury) & Galarraga, L. (Jury), 16 Nov 2020
Student thesis: Doc types › Doctor of Sciences

File

Cite this

@inproceedings{25b098bd11124ba9bf3344c69c646289,

title = "User-Based Experiment Guidelines for Measuring Interpretability in Machine Learning",

abstract = "With the advent of high-performance black-box models, interpretability is becoming a hot topic today in machine learning. While a lot of research isdone on interpretability, machine learning researchers do not have precise guidelines for setting up user-based experiments. This paper provides well-established guidelines from the human-computer interaction community.",

keywords = "Machine learning, Interpretability, Guidelines",

author = "Adrien Bibal and Bruno Dumas and Beno{\^i}t Fr{\'e}nay",

year = "2019",

language = "English",

booktitle = "EGC Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence",

}

TY - GEN

T1 - User-Based Experiment Guidelines for Measuring Interpretability in Machine Learning

AU - Bibal, Adrien

AU - Dumas, Bruno

AU - Frénay, Benoît

PY - 2019

Y1 - 2019

N2 - With the advent of high-performance black-box models, interpretability is becoming a hot topic today in machine learning. While a lot of research isdone on interpretability, machine learning researchers do not have precise guidelines for setting up user-based experiments. This paper provides well-established guidelines from the human-computer interaction community.

AB - With the advent of high-performance black-box models, interpretability is becoming a hot topic today in machine learning. While a lot of research isdone on interpretability, machine learning researchers do not have precise guidelines for setting up user-based experiments. This paper provides well-established guidelines from the human-computer interaction community.

KW - Machine learning

KW - Interpretability

KW - Guidelines

M3 - Conference contribution

BT - EGC Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence

CY - Metz, France

ER -

User-Based Experiment Guidelines for Measuring Interpretability in Machine Learning

Abstract

Keywords

Access to Document

Fingerprint

Student theses

Interpretability and Explainability in Machine Learning and their Application to Nonlinear Dimensionality Reduction

Cite this