Salvato in:
Dettagli Bibliografici
Autori principali: Robeer, Marcel, Bron, Michiel, Herrewijnen, Elize, Hoeseni, Riwish, Bex, Floris
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.15257
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912130988507136
author Robeer, Marcel
Bron, Michiel
Herrewijnen, Elize
Hoeseni, Riwish
Bex, Floris
author_facet Robeer, Marcel
Bron, Michiel
Herrewijnen, Elize
Hoeseni, Riwish
Bex, Floris
contents We present the Explabox: an open-source toolkit for transparent and responsible machine learning (ML) model development and usage. Explabox aids in achieving explainable, fair and robust models by employing a four-step strategy: explore, examine, explain and expose. These steps offer model-agnostic analyses that transform complex 'ingestibles' (models and data) into interpretable 'digestibles'. The toolkit encompasses digestibles for descriptive statistics, performance metrics, model behavior explanations (local and global), and robustness, security, and fairness assessments. Implemented in Python, Explabox supports multiple interaction modes and builds on open-source packages. It empowers model developers and testers to operationalize explainability, fairness, auditability, and security. The initial release focuses on text data and models, with plans for expansion. Explabox's code and documentation are available open-source at https://explabox.readthedocs.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15257
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Explabox: Model-Agnostic Machine Learning Transparency & Analysis
Robeer, Marcel
Bron, Michiel
Herrewijnen, Elize
Hoeseni, Riwish
Bex, Floris
Machine Learning
Artificial Intelligence
Software Engineering
I.2; D.2.5
We present the Explabox: an open-source toolkit for transparent and responsible machine learning (ML) model development and usage. Explabox aids in achieving explainable, fair and robust models by employing a four-step strategy: explore, examine, explain and expose. These steps offer model-agnostic analyses that transform complex 'ingestibles' (models and data) into interpretable 'digestibles'. The toolkit encompasses digestibles for descriptive statistics, performance metrics, model behavior explanations (local and global), and robustness, security, and fairness assessments. Implemented in Python, Explabox supports multiple interaction modes and builds on open-source packages. It empowers model developers and testers to operationalize explainability, fairness, auditability, and security. The initial release focuses on text data and models, with plans for expansion. Explabox's code and documentation are available open-source at https://explabox.readthedocs.io/.
title The Explabox: Model-Agnostic Machine Learning Transparency & Analysis
topic Machine Learning
Artificial Intelligence
Software Engineering
I.2; D.2.5
url https://arxiv.org/abs/2411.15257