Interpretability of Machine Learning Models and Representations: an Introduction

Adrien Bibal; Benoît Frénay

Interpretability of Machine Learning Models and Representations: an Introduction

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

1139 Downloads (Pure)

Abstract

Interpretability is often a major concern in machine learning. Although
many authors agree with this statement, interpretability is often tackled
with intuitive arguments, distinct (yet related) terms and heuristic quan-
tifications. This short survey aims to clarify the concepts related to interpretability and emphasises the distinction between interpreting models
and representations, as well as heuristic-based and user-based approaches.

Original language	English
Title of host publication	24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Subtitle of host publication	ESANN 2016 : Bruges, Belgium, April 27-28-29, 2016 : proceedings
Editors	Michel Verleysen
Place of Publication	Bruges
Publisher	CIACO
Pages	77-82
ISBN (Electronic)	978-287587027-8
ISBN (Print)	978-2-87587-026-1
Publication status	Published - 2016
Event	24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Bruges, Belgium Duration: 27 Apr 2016 → 29 May 2016 Conference number: 24

Conference

Conference	24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Abbreviated title	ESANN 2016
Country/Territory	Belgium
City	Bruges
Period	27/04/16 → 29/05/16

Access to Document

2016-Bibal-Interpretability of Machine Learning Models - an IntroductionAccepted author manuscript, 221 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{612762a86d814268bf8c59d5acc5e1a2,

title = "Interpretability of Machine Learning Models and Representations: an Introduction",

abstract = "Interpretability is often a major concern in machine learning. Althoughmany authors agree with this statement, interpretability is often tackledwith intuitive arguments, distinct (yet related) terms and heuristic quan-tifications. This short survey aims to clarify the concepts related to interpretability and emphasises the distinction between interpreting modelsand representations, as well as heuristic-based and user-based approaches.",

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

year = "2016",

language = "English",

isbn = "978-2-87587-026-1",

pages = "77--82",

editor = "Michel Verleysen",

booktitle = "24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",

publisher = "CIACO ",

note = "24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2016 ; Conference date: 27-04-2016 Through 29-05-2016",

}

Bibal, A & Frénay, B 2016, Interpretability of Machine Learning Models and Representations: an Introduction. in M Verleysen (ed.), 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2016 : Bruges, Belgium, April 27-28-29, 2016 : proceedings. CIACO , Bruges, pp. 77-82, 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 27/04/16.

Interpretability of Machine Learning Models and Representations: an Introduction. / Bibal, Adrien ; Frénay, Benoît.
24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2016 : Bruges, Belgium, April 27-28-29, 2016 : proceedings. ed. / Michel Verleysen. Bruges: CIACO , 2016. p. 77-82.

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

TY - GEN

T1 - Interpretability of Machine Learning Models and Representations

T2 - 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

AU - Bibal, Adrien

AU - Frénay, Benoît

N1 - Conference code: 24

PY - 2016

Y1 - 2016

N2 - Interpretability is often a major concern in machine learning. Althoughmany authors agree with this statement, interpretability is often tackledwith intuitive arguments, distinct (yet related) terms and heuristic quan-tifications. This short survey aims to clarify the concepts related to interpretability and emphasises the distinction between interpreting modelsand representations, as well as heuristic-based and user-based approaches.

AB - Interpretability is often a major concern in machine learning. Althoughmany authors agree with this statement, interpretability is often tackledwith intuitive arguments, distinct (yet related) terms and heuristic quan-tifications. This short survey aims to clarify the concepts related to interpretability and emphasises the distinction between interpreting modelsand representations, as well as heuristic-based and user-based approaches.

M3 - Conference contribution

SN - 978-2-87587-026-1

SP - 77

EP - 82

BT - 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

A2 - Verleysen, Michel

PB - CIACO

CY - Bruges

Y2 - 27 April 2016 through 29 May 2016

ER -

Interpretability of Machine Learning Models and Representations: an Introduction

Abstract

Conference

Access to Document

Fingerprint

Student theses

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

Cite this